---
type: "firecrawl-provider"
description: "Anthropic's Claude product site, claude.com: plan and API pricing as structured data, the resources library (articles, announcements, guides, webinars, videos) with dates, customer stories with industry, product and region, the connectors and plugins marketplace (publisher, categories, surfaces, MCP server URL), search over the claude.com help docs, and any claude.com page or help docs page as clean Markdown. Public pages and the JSON the site's own pages call; no login, key or claude.ai access."
use_when: "Anthropic's Claude product site, claude.com: plan and API pricing as structured data, the resources library (articles, announcements, guides, webinars, videos) with dates, customer stories with industry, product and region, the connectors and plugins marketplace (publisher, categories, surfaces, MCP server URL), search over the claude.com help docs, and any claude.com page or help docs page as clean Markdown. Public pages and the JSON the site's own pages call; no login, key or claude.ai access."
categories: "AI models"
capabilities: 6
credits_per_call: 5
---
# Claude (claude.com) on Firecrawl Alexandria

Anthropic's Claude product site, claude.com: plan and API pricing as structured data, the resources library (articles, announcements, guides, webinars, videos) with dates, customer stories with industry, product and region, the connectors and plugins marketplace (publisher, categories, surfaces, MCP server URL), search over the claude.com help docs, and any claude.com page or help docs page as clean Markdown. Public pages and the JSON the site's own pages call; no login, key or claude.ai access.

- Categories: AI models
- Category index: [AI models category](https://firecrawl.dev/alexandria/agents/categories/ai-models)
- Provider key: `claude-com`
- Access: Firecrawl credits
- Cost: 5 credits per call

## More

- [Human guide](https://firecrawl.dev/app/alexandria/claude-com)
- [OpenAPI spec](https://firecrawl.dev/alexandria/agents/providers/claude-com/openapi.json)

## Capabilities

- [Get page](https://firecrawl.dev/alexandria/agents/providers/claude-com/product-website/get_page): Any public claude.com page as clean Markdown: product, solution, feature and pricing pages, resources articles and guides, customer stories, marketplace connector and plugin pages, event and program pages (/code-with-claude, /programs/startups), localized copies (/de/..., /ja/...), and the claude.com help docs under /docs (read from their Markdown twins). Returns the title, meta description, publication date (articles), page facts (article category, product, date and reading time; customer industry, size, product and location; connector maker), an outline of headings (level, text, anchor) and the content. Pass `section` (heading text or anchor, case-insensitive) for one heading's subtree and `max_chars` to cap the content. Unknown pages, pages that redirect off claude.com (unknown paths redirect to claude.ai) and unknown sections are `not_found`.
- [Get pricing](https://firecrawl.dev/alexandria/agents/providers/claude-com/product-website/get_pricing): Claude plans and prices from claude.com/pricing as structured data, per tab: Individual (Free, Pro, Max), Team and Enterprise (seat prices, annual and monthly), and API (current and legacy model prices per million tokens for input, output and prompt caching read and write, with long-prompt tiers, plus priced platform features such as Managed Agents, web search and code execution), with disclaimers and notes and the pricing FAQ. Set `include_comparison` for the full feature comparison tables, and `segment` for one tab. Prices are the US dollar prices the page server-renders.
- [List customers](https://firecrawl.dev/alexandria/agents/providers/claude-com/product-website/list_customers): Claude customer stories from claude.com/customers, newest first, read from the story list the page embeds (every story, not just the featured ones): customer name, headline, story URL, publication date, industries, company size, Claude products, partner and region. Filter by `q` (name, headline or slug), `industry`, `product`, `company_size`, `region` and `partner` (slug or name, case-insensitive); `facets` lists the accepted values. Window with `limit`/`offset` or the continuation.
- [List marketplace](https://firecrawl.dev/alexandria/agents/providers/claude-com/product-website/list_marketplace): Entries of the Claude connectors and plugins marketplace (claude.com/marketplace), read from the directory list the marketplace pages embed: every connector (about 1,000 remote MCP servers and desktop extensions) or every plugin (about 340). Each entry has its stable id, name, slug, claude.com URL, one-line description, publisher, categories, the Claude surfaces it works with, connector type, MCP server URL, verification, install or popularity numbers and the date added. Filter by `query` (name, slug, description or publisher), `category`, `works_with` and `connector_type`; `slug` returns one entry (`not_found` when absent). Sort like the site: `popular` (default), `trending`, `new` or `alphabetical`. `facets` counts every category and surface. Window with `limit`/`offset` or the continuation.
- [Search docs](https://firecrawl.dev/alexandria/agents/providers/claude-com/product-website/search_docs): Search the claude.com help docs (Claude.ai Documentation: connectors and the Connectors Directory, MCP tunnels, plugins, skills, Claude Tag, Claude Science, Cowork, Office agents, government and third-party deployments) through Anthropic's public Mintlify docs MCP server. Returns ranked hits in the vendor's order with title, URL, page path, section anchor and a Markdown snippet. The search is semantic, so unusual queries can return loosely related hits. Claude Code docs (code.claude.com) and Claude Platform API docs (platform.claude.com) are separate sources.
- [Search resources](https://firecrawl.dev/alexandria/agents/providers/claude-com/product-website/search_resources): Search and list the claude.com resources library (articles and announcements, guides, webinars, videos) newest first, through the same JSON search the site's resources pages call. Filter by full-text `query`, `type`, `category`, `product` and `use_case`; each row has the type, title, URL, date, excerpt, category, products and reading time (webinars add session time, time zone and recording flags). Pages hold 12 rows; pass `page` or follow the continuation. The site serves at most 20 pages (240 rows) per search, so a `result_cap` warning tells you to narrow the filter when `total` exceeds that.

## 1. Choose this provider when

Anthropic's Claude product site, claude.com: plan and API pricing as structured data, the resources library (articles, announcements, guides, webinars, videos) with dates, customer stories with industry, product and region, the connectors and plugins marketplace (publisher, categories, surfaces, MCP server URL), search over the claude.com help docs, and any claude.com page or help docs page as clean Markdown. Public pages and the JSON the site's own pages call; no login, key or claude.ai access.

## 2. Minimal request

Call `POST https://api.firecrawl.dev/v2/scrape` with `{ alexandria: { provider, capability, options } }`. For a batch, send `{ alexandria: [...] }` with up to 10 calls.

```json
{
  "provider": "claude-com",
  "capability": "product-website/get_page",
  "options": {
    "max_chars": 1500,
    "url": "https://claude.com/resources/articles/1m-context"
  }
}
```

## 3. Add provider options

Use only the options needed for the task:

- `max_chars` (number): Cut `content` to this many characters; the full text is returned when omitted. Example: `200`
- `path` (string): A claude.com path instead of `url`, e.g. `/pricing`, `resources/articles/1m-context` or `docs/connectors/mcp-tunnels/overview` (search_docs returns these). Example: `<path>`
- `section` (string): Heading text or anchor whose subtree to return, e.g. `API pricing` or `api-pricing`. Example: `API pricing`
- `url` (string): A claude.com URL, e.g. https://claude.com/customers/adalat-ai or https://claude.com/docs/connectors/directory. A `#anchor` selects that section. claude.ai and other hosts are refused. Pattern: ^https?://. Example: `#anchor`

## 4. Request through your preferred interface

### JavaScript

```javascript
const result = await firecrawl.scrape({
  alexandria: {
    provider: "claude-com",
    capability: "product-website/get_page",
    options: {
      max_chars: 1500,
      url: "https://claude.com/resources/articles/1m-context",
    },
  },
});
```

### Python

```python
result = firecrawl.scrape_alexandria({
  "provider": "claude-com",
  "capability": "product-website/get_page",
  "options": {
    "max_chars": 1500,
    "url": "https://claude.com/resources/articles/1m-context"
  }
})
```

### cURL

```sh
curl https://api.firecrawl.dev/v2/scrape \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "alexandria": {
    "provider": "claude-com",
    "capability": "product-website/get_page",
    "options": {
      "max_chars": 1500,
      "url": "https://claude.com/resources/articles/1m-context"
    }
  }
}'
```

### CLI

```sh
firecrawl scrape 'claude-com/product-website/get_page' \
  --options '{"max_chars":1500,"url":"https://claude.com/resources/articles/1m-context"}'
```


### MCP

Call the FCX MCP retrieve tool with this object:

```json
{
  "provider": "claude-com",
  "capability": "product-website/get_page",
  "options": {
    "max_chars": 1500,
    "url": "https://claude.com/resources/articles/1m-context"
  }
}
```

Ask for only the returned fields needed by the task.

## 5. Full request shape

```json
{
  "provider": "claude-com",
  "capability": "product-website/get_page",
  "options": {
    "max_chars": 1500,
    "url": "https://claude.com/resources/articles/1m-context"
  }
}
```

## 6. Response data

The response includes `success`, `provider`, `capability`, `creditsCost` and `data`. This example shows the provider payload in `data`:

```json
{
  "chars": 3627,
  "content": "# Claude Sonnet 4 now supports 1M tokens of context\n\n***Update:** Now available on Google Cloud's Vertex AI (Aug 26, 2025)*\n\nClaude Sonnet 4 now supports up to 1 million tokens of context on the Anthropic API—a 5x increase that lets you process entire codebases with over 75,000 lines of code or dozens of research papers in a single request.\n\nLong context support for Sonnet 4 is now in public beta on the Claude Developer Platform natively, and in Amazon Bedrock and Google Cloud’s Vertex AI.\n\n### Longer context, more use cases\n\nWith longer context, developers can run more comprehensive and data-intensive use cases with Claude, including:\n\n- **Large-scale code analysis:** Load entire codebases including source files, tests, and documentation. Claude can understand project architecture, identify cross-file dependencies, and suggest improvements that account for the complete system design.\n- **Document synthesis:** Process extensive document sets like legal contracts, research papers, or technical specifications. Analyze relationships across hundreds of documents while maintaining full context.\n- **Context-aware agents:** Build agents that maintain context across hundreds of tool calls and multi-step workflows. Include complete API documentation, tool definitions, and interaction histories without losing coherence.\n\n### API pricing\n\nTo account for increased computational requirements, [pricing](https://www.anthropic.com/pricing#api) adjusts for prompts over 200K tokens:\n\n|  | Inpu",
  "description": "Claude Sonnet 4 now supports up to 1 million tokens of context—a 5x increase that lets you process entire codebases, synthesize extensive document sets, and build agents that maintain coherence across hundreds of tool calls.",
  "facts": [
    {
      "label": "Category",
      "value": "Announcements"
    },
    {
      "label": "Product",
      "value": "Claude apps"
    },
    {
      "label": "Date",
      "value": "August 12, 2025"
    },
    {
      "label": "Reading time",
      "value": "4 min"
    }
  ],
  "kind": "article",
  "markdown_url": null,
  "observed_at_ms": 1792694709524,
  "outline": [
    {
      "anchor": "longer-context-more-use-cases",
      "level": 3,
      "text": "Longer context, more use cases"
    },
    {
      "anchor": "api-pricing",
      "level": 3,
      "text": "API pricing"
    },
    {
      "anchor": "customer-spotlight-bolt-new",
      "level": 3,
      "text": "Customer spotlight: Bolt.new"
    },
    {
      "anchor": "customer-spotlight-igent-ai",
      "level": 3,
      "text": "Customer spotlight: iGent AI"
    },
    {
      "anchor": "get-started",
      "level": 3,
      "text": "Get started"
    }
  ],
  "path": "resources/articles/1m-context",
  "published_date": "2025-08-12",
  "section": null,
  "title": "Claude Sonnet 4 now supports 1M tokens of context",
  "truncated": true,
  "url": "https://claude.com/resources/articles/1m-context"
}
```

## API reference-derived contract

The following capability contract is generated from the same normalized Alexandria API reference exposed in the API spec.

### Get page

- Capability: `product-website/get_page`
- Description: Any public claude.com page as clean Markdown: product, solution, feature and pricing pages, resources articles and guides, customer stories, marketplace connector and plugin pages, event and program pages (/code-with-claude, /programs/startups), localized copies (/de/..., /ja/...), and the claude.com help docs under /docs (read from their Markdown twins). Returns the title, meta description, publication date (articles), page facts (article category, product, date and reading time; customer industry, size, product and location; connector maker), an outline of headings (level, text, anchor) and the content. Pass `section` (heading text or anchor, case-insensitive) for one heading's subtree and `max_chars` to cap the content. Unknown pages, pages that redirect off claude.com (unknown paths redirect to claude.ai) and unknown sections are `not_found`.
- Instructions: To read a claude.com page an agent was given or found: a customer story, an announcement article, a product page such as /product/claude-code, a solutions page, or a claude.com help docs page (connectors, plugins, skills, Claude Tag, Claude Science, government). Also reads one marketplace entry's full page (/marketplace/connectors/{slug}). For structured prices use get_pricing; for lists use search_resources, list_customers and list_marketplace.
- Cost: 5 credits per call
- Capability file: [Get page](https://firecrawl.dev/alexandria/agents/providers/claude-com/product-website/get_page)

Accepted options:
- `max_chars` (number): Cut `content` to this many characters; the full text is returned when omitted. Example: `200`
- `path` (string): A claude.com path instead of `url`, e.g. `/pricing`, `resources/articles/1m-context` or `docs/connectors/mcp-tunnels/overview` (search_docs returns these). Example: `<path>`
- `section` (string): Heading text or anchor whose subtree to return, e.g. `API pricing` or `api-pricing`. Example: `API pricing`
- `url` (string): A claude.com URL, e.g. https://claude.com/customers/adalat-ai or https://claude.com/docs/connectors/directory. A `#anchor` selects that section. claude.ai and other hosts are refused. Pattern: ^https?://. Example: `#anchor`

Response schema example:
```json
{
  "chars": 3627,
  "content": "# Claude Sonnet 4 now supports 1M tokens of context\n\n***Update:** Now available on Google Cloud's Vertex AI (Aug 26, 2025)*\n\nClaude Sonnet 4 now supports up to 1 million tokens of context on the Anthropic API—a 5x increase that lets you process entire codebases with over 75,000 lines of code or dozens of research papers in a single request.\n\nLong context support for Sonnet 4 is now in public beta on the Claude Developer Platform natively, and in Amazon Bedrock and Google Cloud’s Vertex AI.\n\n### Longer context, more use cases\n\nWith longer context, developers can run more comprehensive and data-intensive use cases with Claude, including:\n\n- **Large-scale code analysis:** Load entire codebases including source files, tests, and documentation. Claude can understand project architecture, identify cross-file dependencies, and suggest improvements that account for the complete system design.\n- **Document synthesis:** Process extensive document sets like legal contracts, research papers, or technical specifications. Analyze relationships across hundreds of documents while maintaining full context.\n- **Context-aware agents:** Build agents that maintain context across hundreds of tool calls and multi-step workflows. Include complete API documentation, tool definitions, and interaction histories without losing coherence.\n\n### API pricing\n\nTo account for increased computational requirements, [pricing](https://www.anthropic.com/pricing#api) adjusts for prompts over 200K tokens:\n\n|  | Inpu",
  "description": "Claude Sonnet 4 now supports up to 1 million tokens of context—a 5x increase that lets you process entire codebases, synthesize extensive document sets, and build agents that maintain coherence across hundreds of tool calls.",
  "facts": [
    {
      "label": "Category",
      "value": "Announcements"
    },
    {
      "label": "Product",
      "value": "Claude apps"
    },
    {
      "label": "Date",
      "value": "August 12, 2025"
    },
    {
      "label": "Reading time",
      "value": "4 min"
    }
  ],
  "kind": "article",
  "markdown_url": null,
  "observed_at_ms": 1792694709524,
  "outline": [
    {
      "anchor": "longer-context-more-use-cases",
      "level": 3,
      "text": "Longer context, more use cases"
    },
    {
      "anchor": "api-pricing",
      "level": 3,
      "text": "API pricing"
    },
    {
      "anchor": "customer-spotlight-bolt-new",
      "level": 3,
      "text": "Customer spotlight: Bolt.new"
    },
    {
      "anchor": "customer-spotlight-igent-ai",
      "level": 3,
      "text": "Customer spotlight: iGent AI"
    },
    {
      "anchor": "get-started",
      "level": 3,
      "text": "Get started"
    }
  ],
  "path": "resources/articles/1m-context",
  "published_date": "2025-08-12",
  "section": null,
  "title": "Claude Sonnet 4 now supports 1M tokens of context",
  "truncated": true,
  "url": "https://claude.com/resources/articles/1m-context"
}
```

### Get pricing

- Capability: `product-website/get_pricing`
- Description: Claude plans and prices from claude.com/pricing as structured data, per tab: Individual (Free, Pro, Max), Team and Enterprise (seat prices, annual and monthly), and API (current and legacy model prices per million tokens for input, output and prompt caching read and write, with long-prompt tiers, plus priced platform features such as Managed Agents, web search and code execution), with disclaimers and notes and the pricing FAQ. Set `include_comparison` for the full feature comparison tables, and `segment` for one tab. Prices are the US dollar prices the page server-renders.
- Instructions: To answer what a Claude plan costs, what each plan includes, how Team seats are priced, or what a Claude model costs per token as claude.com shows it.
- Cost: 5 credits per call
- Capability file: [Get pricing](https://firecrawl.dev/alexandria/agents/providers/claude-com/product-website/get_pricing)

Accepted options:
- `include_comparison` (boolean): Include the feature comparison tables. Defaults to false. Example: `false`
- `segment` (string): Only this tab. Defaults to every tab. Example: `individual`

Response schema example:
```json
{
  "currency": "USD",
  "faq": [
    {
      "answer": "The Pro plan gives you everything in a Free plan with more usage and more of Claude's capabilities. That includes Claude Code, along with projects to organize your chats and documents, access to more Claude models, and Claude for Microsoft 365. You can choose a monthly or annual subscription.",
      "question": "What do I get with Claude Pro?"
    },
    {
      "answer": "The Max plan is built for people who work with Claude throughout the day and want longer, uninterrupted sessions. You get everything in Pro, plus more usage: choose from 5x or 20x the usage of Pro per 5-hour session. Max also gives you higher output limits. Both options are billed monthly. See the cards above for current pricing.",
      "question": "How is Claude Max different from Pro?"
    },
    {
      "answer": "Every plan has usage limits that reset on a rolling five-hour session window, and paid plans add weekly limits on top. Your activity across Claude on web, desktop, mobile, and Claude Code all draws from the same pool. How much you can do depends on the length and complexity of your conversations, the model you choose, and the features you use, so there's no fixed message count. Free covers everyday questions. Pro gives you at least 5x more usage per 5-hour session than Free. Max gives you 5x or 20x more usage per 5-hour session than Pro. On Team plans, Standard seats give more than Pro and Premium seats give 5x more than Standard. To manage capacity and make sure all users have fair access, we may limit your usage in other ways, such as weekly and monthly caps or model and feature usage, at our discretion. When you reach a limit, you can wait for it to reset, move to a higher plan, or, on paid plans, turn on usage credits to keep working at standard API rates. You can see where you stand anytime in Settings > Usage.",
      "question": "What are the usage limits on each plan, and what happens when I hit them?"
    },
    {
      "answer": "Claude Code is included in all paid plans. It shares the same usage limits as the rest of your plan, so your work in the terminal and your chats draw from one pool. For heavy coding sessions, you can also switch to pay-as-you-go API credits through a Console account.",
      "question": "Is Claude Code included in my plan?"
    },
    {
      "answer": "The Claude Enterprise plan is built for large businesses operating at scale. Pricing is $20 per seat per month plus usage billed at API rates, so cost scales with the models and tasks your team runs. Enterprise is billed annually and includes everything in Team plus advanced security and admin controls, including SCIM, audit logs, custom data retention, and role-based access. You can get started self-serve or contact sales for a tailored quote.",
      "question": "How much does the Claude Enterprise plan cost?"
    },
    {
      "answer": "Yes, annual plans are designed to cost less than monthly subscriptions. Annual subscriptions are available for Pro and Team plans. Enterprise plans are only available as annual subscriptions. When you choose to pay annually, you're billed once up front for the year. If you're already on a monthly plan, you can switch to annual in Settings > Billing, and any unused time is credited toward your first annual invoice. See the steps for Pro and Team.",
      "question": "Can I pay annually? Does it cost less than if I pay monthly?"
    },
    {
      "answer": "Payments are generally non-refundable, except where our Consumer Terms of Service say otherwise or where local law requires it. Customers outside of Europe can follow this process to request a refund: Log in, open Get help from the menu, start a message, and choose Claude Refund Request to check your eligibility. If you subscribed through the App Store, Apple handles the refund, so you'll request it from Apple. If you subscribed through Google Play, contact our Support team to check eligibility for an active subscription. If you're in the European Economic Area and the United Kingdom, and within your 14-day withdrawal period, you can request a refund directly in the app.",
      "question": "Does Claude offer refunds?"
    },
    {
      "answer": "You can change your plan any time in Settings. For individual plans, go to Settings > Billing and choose Manage subscription. On Team plans, an Owner or Primary Owner manages this under Organization settings > Billing. See more details here. Upgrades take effect right away, and any unused time on your current plan is credited toward the new one, so you won't pay twice for the same days. Moving from monthly to annual works the same way, with your remaining time credited to the first annual invoice. In some upgrades (for example Pro Annual to Max 5x Monthly), your remaining value on your old plan is larger than the cost of one billing period of the new plan. In this case, the excess will be stored as credit, which will automatically get used for future purchases. Downgrades take effect at the end of your current billing period, and your chats, projects, and files stay with your account whichever plan you're on.",
      "question": "How do I upgrade, downgrade, or switch between plans?"
    },
    {
      "answer": "You can cancel anytime, and your plan stays active until the end of your current billing period. To avoid the next charge, cancel at least 24 hours before your renewal date. If you signed up on the web or the desktop app, go to Settings > Billing and click Cancel. If you subscribed through the App Store or Google Play, cancel from that app under Billing > Manage subscription, or directly in your Apple or Google Play account. Team and self-serve Enterprise: an Owner or Primary Owner cancels under Organization settings > Billing. Sales-assisted Enterprise: Reach out to your Anthropic Contact or our Sales team to discuss cancellation. Canceling doesn't delete your data. Your chats, projects, and files stay with your account, though some features aren't available on the Free plan. For Pro and Max, your account moves to the Free plan once the period ends. For step-by-step help, see how to cancel a Pro or Max plan or cancel a Team plan.",
      "question": "How do I cancel my Claude subscription?"
    }
  ],
  "observed_at_ms": 1792694709302,
  "segment": null,
  "segments": [
    {
      "api_models": [],
      "comparison": null,
      "label": "Individual",
      "notes": [
        "Usage limits apply. Prices shown don’t include applicable tax. Price and plans are subject to change at Anthropic's discretion.",
        "Usage limits apply. Price and plans are subject to change at Anthropic's discretion."
      ],
      "plans": [
        {
          "features": [
            "Chat on web, desktop, and mobile",
            "Search the web, create files, and run code",
            "Memory across conversations",
            "Connect your apps and tools",
            "Create Artifacts",
            "Claude Design, Slides, Docs"
          ],
          "features_title": null,
          "name": "Free",
          "price_note": "Free for everyone",
          "price_text": "$0",
          "price_usd": 0,
          "prices": [
            {
              "amount_usd": 0,
              "code": "free",
              "field": null,
              "text": "$0"
            }
          ],
          "seats": [],
          "subtitle": "Try Claude"
        },
        {
          "features": [
            "More usage*",
            "Hand off and schedule tasks",
            "Claude Dashboards (beta)",
            "Claude Code",
            "Claude Science",
            "Projects",
            "More Claude models",
            "Claude in Chrome and Microsoft 365"
          ],
          "features_title": "Everything in Free, plus:",
          "name": "Pro",
          "price_note": "Per month with annual subscription discount ($200 billed up front). $20 if billed monthly.",
          "price_text": "$17",
          "price_usd": 17,
          "prices": [
            {
              "amount_usd": 17,
              "code": "pro_annual",
              "field": "amount_per_month",
              "text": "$17"
            },
            {
              "amount_usd": 200,
              "code": "pro_annual",
              "field": "amount_total",
              "text": "$200"
            },
            {
              "amount_usd": 20,
              "code": "pro_monthly",
              "field": null,
              "text": "$20"
            }
          ],
          "seats": [],
          "subtitle": "For everyday work"
        },
        {
          "features": [
            "Choose 5x or 20x more usage than Pro*",
            "Higher output limits for all tasks",
            "Early access to advanced Claude features",
            "Priority access at high traffic times",
            "$100 to $200/month in API credits to build on the Claude Platform†"
          ],
          "features_title": "Everything in Pro, plus:",
          "name": "Max",
          "price_note": "Per month",
          "price_text": "From $100",
          "price_usd": 100,
          "prices": [
            {
              "amount_usd": 100,
              "code": "max_5x_monthly",
              "field": null,
              "text": "From $100"
            }
          ],
          "seats": [],
          "subtitle": "For people who work with Claude all day"
        }
      ],
      "platform_features": [],
      "segment": "individual"
    },
    {
      "api_models": [],
      "comparison": null,
      "label": "Team & Enterprise",
      "notes": [
        "Usage limits apply. Prices shown don’t include applicable tax. Price and plans are subject to change at Anthropic's discretion.",
        "Usage limits apply. Price and plans are subject to change at Anthropic's discretion."
      ],
      "plans": [
        {
          "features": [
            "Claude Code and Claude Cowork",
            "Claude Design, Slides, and Docs",
            "Claude Motion and Dashboards (beta)",
            "Claude Science",
            "Microsoft 365, @Claude, and more",
            "Enterprise search across your organization",
            "Central billing and administration",
            "Single sign-on (SSO)",
            "Admin controls for remote and local connectors",
            "Enterprise deployment for the Claude desktop app",
            "No model training on your content by default",
            "Mix and match seat types",
            "Up to $500 per month in pooled API credits†"
          ],
          "features_title": null,
          "name": "Team",
          "price_note": null,
          "price_text": null,
          "price_usd": null,
          "prices": [
            {
              "amount_usd": 20,
              "code": "team_annual_per_seat",
              "field": "amount_per_month",
              "text": "$20"
            },
            {
              "amount_usd": 25,
              "code": "team_monthly_per_seat",
              "field": null,
              "text": "$25"
            },
            {
              "amount_usd": 100,
              "code": "team_premium_annual_per_seat",
              "field": "amount_per_month",
              "text": "$100"
            },
            {
              "amount_usd": 125,
              "code": "team_premium_monthly_per_seat",
              "field": null,
              "text": "$125"
            }
          ],
          "seats": [
            {
              "description": "All Claude features, plus more usage than Pro*",
              "name": "Standard seat",
              "note": "Per seat / month if billed annually. $25 if billed monthly.",
              "price_text": "$20",
              "price_usd": 20
            },
            {
              "description": "5x more usage than standard seats*",
              "name": "Premium seat",
              "note": "Per seat / month if billed annually. $125 if billed monthly.",
              "price_text": "$100",
              "price_usd": 100
            }
          ],
          "subtitle": "For teams of 2 to 150"
        },
        {
          "features": [
            "Admins set user and org spend limits",
            "Role-based access with fine grained permissioning",
            "System for Cross-domain Identity Management (SCIM)",
            "Audit logs",
            "Compliance API for observability and monitoring",
            "Custom data retention controls",
            "Network-level access control",
            "IP allowlisting",
            "HIPAA-ready offering available",
            "Claude Security (beta)"
          ],
          "features_title": "All Team plan features, plus:",
          "name": "Enterprise",
          "price_note": null,
          "price_text": null,
          "price_usd": null,
          "prices": [],
          "seats": [
            {
              "description": null,
              "name": "Seat price + usage at API rates",
              "note": "US$20/seat/month, billed annually, 20 seat minimum. Usage cost scales with model and task.",
              "price_text": null,
              "price_usd": null
            }
          ],
          "subtitle": "For large businesses operating at scale"
        }
      ],
      "platform_features": [],
      "segment": "team_enterprise"
    },
    {
      "api_models": [
        {
          "legacy": false,
          "name": "Fable 5.1",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.25 / MTok",
              "usd_per_mtok": 0.25,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$12.50 / MTok",
              "usd_per_mtok": 12.5,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$10 / MTok",
              "usd_per_mtok": 10,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$50 / MTok",
              "usd_per_mtok": 50,
              "variant": null
            }
          ],
          "subtitle": "Next generation intelligence for long-running agents"
        },
        {
          "legacy": false,
          "name": "Opus 5.5",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.20 / MTok",
              "usd_per_mtok": 0.2,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$5 / MTok",
              "usd_per_mtok": 5,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$4 / MTok",
              "usd_per_mtok": 4,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$20 / MTok",
              "usd_per_mtok": 20,
              "variant": null
            }
          ],
          "subtitle": "Daily driver for agentic coding and enterprise work"
        },
        {
          "legacy": false,
          "name": "Sonnet 5.5",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.10 / MTok",
              "usd_per_mtok": 0.1,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$2.50 / MTok",
              "usd_per_mtok": 2.5,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$2 / MTok",
              "usd_per_mtok": 2,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$10 / MTok",
              "usd_per_mtok": 10,
              "variant": null
            }
          ],
          "subtitle": "High-performance model for coding and agents"
        },
        {
          "legacy": false,
          "name": "Haiku 5.5",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.01 / MTok",
              "usd_per_mtok": 0.01,
              "variant": "Prompts ≤ 100K tokens, Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$0.125 / MTok",
              "usd_per_mtok": 0.125,
              "variant": "Prompts ≤ 100K tokens, Write"
            },
            {
              "item": "Prompt caching",
              "price_text": "$0.05 / MTok",
              "usd_per_mtok": 0.05,
              "variant": "Prompts > 100K tokens, Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$0.625 / MTok",
              "usd_per_mtok": 0.625,
              "variant": "Prompts > 100K tokens, Write"
            },
            {
              "item": "Input",
              "price_text": "$0.10 / MTok",
              "usd_per_mtok": 0.1,
              "variant": "Prompts ≤ 100K tokens"
            },
            {
              "item": "Input",
              "price_text": "$0.50 / MTok",
              "usd_per_mtok": 0.5,
              "variant": "Prompts > 100K tokens"
            },
            {
              "item": "Output",
              "price_text": "$0.50 / MTok",
              "usd_per_mtok": 0.5,
              "variant": "Prompts ≤ 100K tokens"
            },
            {
              "item": "Output",
              "price_text": "$2.50 / MTok",
              "usd_per_mtok": 2.5,
              "variant": "Prompts > 100K tokens"
            }
          ],
          "subtitle": "Fastest, most cost-efficient model"
        },
        {
          "legacy": true,
          "name": "Haiku 4.5",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.10 / MTok",
              "usd_per_mtok": 0.1,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$1.25 / MTok",
              "usd_per_mtok": 1.25,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$1 / MTok",
              "usd_per_mtok": 1,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$5 / MTok",
              "usd_per_mtok": 5,
              "variant": null
            }
          ],
          "subtitle": null
        },
        {
          "legacy": true,
          "name": "Sonnet 5",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.20 / MTok",
              "usd_per_mtok": 0.2,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$2.50 / MTok",
              "usd_per_mtok": 2.5,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$2 / MTok",
              "usd_per_mtok": 2,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$10 / MTok",
              "usd_per_mtok": 10,
              "variant": null
            }
          ],
          "subtitle": null
        },
        {
          "legacy": true,
          "name": "Opus 5",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.50 / MTok",
              "usd_per_mtok": 0.5,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$6.25 / MTok",
              "usd_per_mtok": 6.25,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$5 / MTok",
              "usd_per_mtok": 5,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$25 / MTok",
              "usd_per_mtok": 25,
              "variant": null
            }
          ],
          "subtitle": null
        },
        {
          "legacy": true,
          "name": "Fable 5",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$1 / MTok",
              "usd_per_mtok": 1,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$12.50 / MTok",
              "usd_per_mtok": 12.5,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$10 / MTok",
              "usd_per_mtok": 10,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$50 / MTok",
              "usd_per_mtok": 50,
              "variant": null
            }
          ],
          "subtitle": null
        },
        {
          "legacy": true,
          "name": "Opus 4.8",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.50 / MTok",
              "usd_per_mtok": 0.5,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$6.25 / MTok",
              "usd_per_mtok": 6.25,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$5 / MTok",
              "usd_per_mtok": 5,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$25 / MTok",
              "usd_per_mtok": 25,
              "variant": null
            }
          ],
          "subtitle": null
        },
        {
          "legacy": true,
          "name": "Sonnet 4.6",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.30 / MTok",
              "usd_per_mtok": 0.3,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$3.75 / MTok",
              "usd_per_mtok": 3.75,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$3 / MTok",
              "usd_per_mtok": 3,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$15 / MTok",
              "usd_per_mtok": 15,
              "variant": null
            }
          ],
          "subtitle": null
        },
        {
          "legacy": true,
          "name": "Opus 4.7",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.50 / MTok",
              "usd_per_mtok": 0.5,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$6.25 / MTok",
              "usd_per_mtok": 6.25,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$5 / MTok",
              "usd_per_mtok": 5,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$25 / MTok",
              "usd_per_mtok": 25,
              "variant": null
            }
          ],
          "subtitle": null
        },
        {
          "legacy": true,
          "name": "Opus 4.6",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.50 / MTok",
              "usd_per_mtok": 0.5,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$6.25 / MTok",
              "usd_per_mtok": 6.25,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$5 / MTok",
              "usd_per_mtok": 5,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$25 / MTok",
              "usd_per_mtok": 25,
              "variant": null
            }
          ],
          "subtitle": null
        },
        {
          "legacy": true,
          "name": "Sonnet 4.5",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.30 / MTok",
              "usd_per_mtok": 0.3,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$3.75 / MTok",
              "usd_per_mtok": 3.75,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$3 / MTok",
              "usd_per_mtok": 3,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$15 / MTok",
              "usd_per_mtok": 15,
              "variant": null
            }
          ],
          "subtitle": null
        },
        {
          "legacy": true,
          "name": "Opus 4.5",
          "prices": [
            {
              "item": "Prompt caching",
              "price_text": "$0.50 / MTok",
              "usd_per_mtok": 0.5,
              "variant": "Read"
            },
            {
              "item": "Prompt caching",
              "price_text": "$6.25 / MTok",
              "usd_per_mtok": 6.25,
              "variant": "Write"
            },
            {
              "item": "Input",
              "price_text": "$5 / MTok",
              "usd_per_mtok": 5,
              "variant": null
            },
            {
              "item": "Output",
              "price_text": "$25 / MTok",
              "usd_per_mtok": 25,
              "variant": null
            }
          ],
          "subtitle": null
        }
      ],
      "comparison": null,
      "label": "API",
      "notes": [
        "For workloads that need to run in the US, US-only inference is available at 1.1x pricing for input and output tokens. Learn more.",
        "Get up to 2.5x faster speeds with fast mode for Opus 5.5 at 2x standard pricing. Learn more.",
        "Prompt caching pricing reflects 5-minute TTL. Learn about extended prompt caching."
      ],
      "plans": [],
      "platform_features": [
        {
          "cost": "$0.08 per session-hour for active runtime",
          "cost_label": "Cost",
          "cost_usd": 0.08,
          "description": "Build and deploy agents at scale with a suite of composable APIs. Standard token rates apply.",
          "name": "Managed Agents"
        },
        {
          "cost": "$10 / 1K searches",
          "cost_label": "Cost",
          "cost_usd": 10,
          "description": "Give Claude access to the latest information from the web. Doesn’t include input and output tokens required to process requests.",
          "name": "Web search"
        },
        {
          "cost": "$0.05 per hour per container",
          "cost_label": "Additional hours",
          "cost_usd": 0.05,
          "description": "Run Python code in a sandboxed environment for advanced data analysis. 50 free hours of usage daily per organization.",
          "name": "Code execution"
        }
      ],
      "segment": "api"
    }
  ],
  "source_url": "https://claude.com/pricing",
  "unrendered_tabs": []
}
```

### List customers

- Capability: `product-website/list_customers`
- Description: Claude customer stories from claude.com/customers, newest first, read from the story list the page embeds (every story, not just the featured ones): customer name, headline, story URL, publication date, industries, company size, Claude products, partner and region. Filter by `q` (name, headline or slug), `industry`, `product`, `company_size`, `region` and `partner` (slug or name, case-insensitive); `facets` lists the accepted values. Window with `limit`/`offset` or the continuation.
- Instructions: To find which companies use Claude for an industry, product or region (case studies), then read a story with get_page.
- Cost: 5 credits per call
- Capability file: [List customers](https://firecrawl.dev/alexandria/agents/providers/claude-com/product-website/list_customers)

Accepted options:
- `company_size` (string): `startup`, `small`, `medium` or `large`. Example: `<company_size>`
- `industry` (string): Industry slug or name, e.g. `financial-services`. Example: `financial-services`
- `limit` (number): Rows to return, 1-300. Defaults to 25. Example: `10`
- `offset` (number): Rows to skip. Defaults to 0. Example: `10`
- `partner` (string): Partner slug or name, e.g. `amazon-web-service` or `AWS`. Example: `amazon-web-service`
- `product` (string): Product slug or name, e.g. `claude-code` or `Claude Platform`. Example: `claude-code`
- `q` (string): Case-insensitive text in the customer name, headline or slug. Example: `<q>`
- `region` (string): Region slug or name, e.g. `europe`, `north-america`, `asia-pacific`. Example: `<region>`

Response schema example:
```json
{
  "company_size": null,
  "count": 1,
  "facets": {
    "company_size": [
      {
        "name": "Large",
        "slug": "large"
      },
      {
        "name": "Medium",
        "slug": "medium"
      },
      {
        "name": "Small",
        "slug": "small"
      },
      {
        "name": "Startup",
        "slug": "startup"
      }
    ],
    "industry": [
      {
        "name": "Automotive",
        "slug": "automotive"
      },
      {
        "name": "Beneficial Deployments",
        "slug": "beneficial-deployments"
      },
      {
        "name": "Cybersecurity",
        "slug": "cybersecurity"
      },
      {
        "name": "Ecommerce",
        "slug": "ecommerce"
      },
      {
        "name": "Education",
        "slug": "education"
      },
      {
        "name": "Energy",
        "slug": "energy"
      },
      {
        "name": "Entertainment",
        "slug": "entertainment"
      },
      {
        "name": "Financial services",
        "slug": "financial-services"
      },
      {
        "name": "Government",
        "slug": "government"
      },
      {
        "name": "Healthcare",
        "slug": "healthcare"
      },
      {
        "name": "Insurance",
        "slug": "insurance"
      },
      {
        "name": "Legal",
        "slug": "legal"
      },
      {
        "name": "Life sciences",
        "slug": "life-sciences"
      },
      {
        "name": "Marketing and advertising",
        "slug": "marketing-and-advertising"
      },
      {
        "name": "Nonprofit",
        "slug": "nonprofit"
      },
      {
        "name": "Professional services",
        "slug": "professional-services"
      },
      {
        "name": "Recruiting",
        "slug": "recruiting"
      },
      {
        "name": "Retail Services",
        "slug": "retail-services"
      },
      {
        "name": "Scientific research",
        "slug": "scientific-research"
      },
      {
        "name": "Software",
        "slug": "software"
      },
      {
        "name": "Telecommunications",
        "slug": "telecommunications"
      },
      {
        "name": "Transportation",
        "slug": "transportation"
      }
    ],
    "partner": [
      {
        "name": "AWS",
        "slug": "amazon-web-service"
      },
      {
        "name": "Accenture",
        "slug": "accenture"
      },
      {
        "name": "Artefact",
        "slug": "artefact"
      },
      {
        "name": "Blank Metal",
        "slug": "blank-metal"
      },
      {
        "name": "Google",
        "slug": "google"
      },
      {
        "name": "Tenex",
        "slug": "tenex"
      }
    ],
    "product": [
      {
        "name": "Claude Agent SDK",
        "slug": "claude-agent-sdk"
      },
      {
        "name": "Claude Code",
        "slug": "claude-code"
      },
      {
        "name": "Claude Cowork",
        "slug": "claude-cowork"
      },
      {
        "name": "Claude Enterprise",
        "slug": "claude-enterprise"
      },
      {
        "name": "Claude Managed Agents",
        "slug": "claude-managed-agents"
      },
      {
        "name": "Claude Platform",
        "slug": "claude-developer-platform"
      },
      {
        "name": "Claude Tag",
        "slug": "claude-tag"
      },
      {
        "name": "Claude for Nonprofits",
        "slug": "claude-for-nonprofits"
      }
    ],
    "region": [
      {
        "name": "Africa",
        "slug": "africa"
      },
      {
        "name": "Asia Pacific",
        "slug": "asia-pacific"
      },
      {
        "name": "Australia",
        "slug": "australia"
      },
      {
        "name": "EMEA",
        "slug": "emea"
      },
      {
        "name": "Europe",
        "slug": "europe"
      },
      {
        "name": "India",
        "slug": "india"
      },
      {
        "name": "Latin America",
        "slug": "latin-america"
      },
      {
        "name": "North America",
        "slug": "north-america"
      },
      {
        "name": "South America",
        "slug": "south-america"
      }
    ]
  },
  "industry": null,
  "observed_at_ms": 1792694709673,
  "offset": 0,
  "partner": null,
  "product": null,
  "q": "stripe",
  "region": null,
  "results": [
    {
      "company_size": {
        "name": "Large",
        "slug": "large"
      },
      "date": "2026-03-06",
      "industries": [
        {
          "name": "Software",
          "slug": "software"
        }
      ],
      "name": "Stripe",
      "partner": null,
      "products": [
        {
          "name": "Claude Code",
          "slug": "claude-code"
        }
      ],
      "region": {
        "name": "North America",
        "slug": "north-america"
      },
      "slug": "stripe",
      "title": "Stripe deploys Claude Code to 1,370 engineers with zero-configuration enterprise rollout",
      "url": "https://claude.com/customers/stripe"
    }
  ],
  "source_url": "https://claude.com/customers",
  "total": 1,
  "total_stories": 284
}
```

### List marketplace

- Capability: `product-website/list_marketplace`
- Description: Entries of the Claude connectors and plugins marketplace (claude.com/marketplace), read from the directory list the marketplace pages embed: every connector (about 1,000 remote MCP servers and desktop extensions) or every plugin (about 340). Each entry has its stable id, name, slug, claude.com URL, one-line description, publisher, categories, the Claude surfaces it works with, connector type, MCP server URL, verification, install or popularity numbers and the date added. Filter by `query` (name, slug, description or publisher), `category`, `works_with` and `connector_type`; `slug` returns one entry (`not_found` when absent). Sort like the site: `popular` (default), `trending`, `new` or `alphabetical`. `facets` counts every category and surface. Window with `limit`/`offset` or the continuation.
- Instructions: To find which connectors or plugins exist for a tool or task (for example a CRM, Google Drive or code review), who publishes them, which Claude surfaces they work with and their MCP server URLs, or to look up one entry by slug. Read an entry's full page with get_page on its URL.
- Cost: 5 credits per call
- Capability file: [List marketplace](https://firecrawl.dev/alexandria/agents/providers/claude-com/product-website/list_marketplace)

Accepted options:
- `category` (string): Connector category slug, e.g. `productivity`, `data-analytics`, `developer-tools` (see `facets.category`). Connectors only. Example: `<category>`
- `connector_type` (string): Connectors only: hosted MCP servers or desktop extensions. Example: `remote`
- `kind` (string): Which directory to read. Defaults to `connectors`. Example: `connectors`
- `limit` (number): Rows to return, 1-200. Defaults to 25. Example: `10`
- `offset` (number): Rows to skip. Defaults to 0. Example: `10`
- `query` (string): Case-insensitive text in the name, slug, description or publisher. Example: `<query>`
- `slug` (string): One entry by slug, e.g. `google-drive` or `frontend-design`. Example: `google-drive`
- `sort` (string): Defaults to `popular`. Example: `popular`
- `works_with` (string): Claude surface: `claude`, `claude-code`, `claude-desktop` or `claude-api`. Example: `<works_with>`

Response schema example:
```json
{
  "category": null,
  "connector_type": null,
  "count": 1,
  "facets": {
    "category": [
      {
        "count": 427,
        "value": "productivity"
      },
      {
        "count": 239,
        "value": "data-analytics"
      },
      {
        "count": 160,
        "value": "financial-services"
      },
      {
        "count": 145,
        "value": "sales-and-marketing"
      },
      {
        "count": 139,
        "value": "developer-tools"
      },
      {
        "count": 81,
        "value": "communication"
      },
      {
        "count": 60,
        "value": "legal"
      },
      {
        "count": 49,
        "value": "creative"
      },
      {
        "count": 36,
        "value": "commerce-shopping"
      },
      {
        "count": 34,
        "value": "other"
      },
      {
        "count": 33,
        "value": "health-life-sciences"
      },
      {
        "count": 27,
        "value": "education"
      },
      {
        "count": 23,
        "value": "travel"
      },
      {
        "count": 15,
        "value": "consumer-health"
      },
      {
        "count": 15,
        "value": "media-entertainment"
      },
      {
        "count": 15,
        "value": "nonprofit"
      },
      {
        "count": 2,
        "value": "healthcare"
      }
    ],
    "works_with": [
      {
        "count": 869,
        "value": "claude"
      },
      {
        "count": 768,
        "value": "claude-api"
      },
      {
        "count": 743,
        "value": "claude-desktop"
      },
      {
        "count": 726,
        "value": "claude-code"
      }
    ]
  },
  "kind": "connectors",
  "observed_at_ms": 1792694709673,
  "offset": 0,
  "query": null,
  "results": [
    {
      "added_at": "2025-11-12T00:00:00.000Z",
      "categories": [
        "productivity"
      ],
      "connector_type": "remote",
      "description": "Connect your Notion workspace to search, update, and power workflows across tools",
      "id": "wf.68b0619053b61cf2e850aa90",
      "installs": null,
      "is_new": false,
      "kind": "connector",
      "name": "Notion",
      "popularity_score": 22369,
      "publisher": "Notion",
      "publisher_url": "https://notion.com/",
      "server_url": "https://mcp.notion.com/mcp",
      "slug": "notion",
      "trending": false,
      "trending_score": 49362,
      "url": "https://claude.com/marketplace/connectors/notion",
      "verified": "partner",
      "works_with": [
        "claude",
        "claude-api",
        "claude-code"
      ]
    }
  ],
  "slug": "notion",
  "sort": "popular",
  "source_url": "https://claude.com/marketplace/connectors-plugins",
  "total": 1,
  "total_entries": 1004,
  "works_with": null
}
```

### Search docs

- Capability: `product-website/search_docs`
- Description: Search the claude.com help docs (Claude.ai Documentation: connectors and the Connectors Directory, MCP tunnels, plugins, skills, Claude Tag, Claude Science, Cowork, Office agents, government and third-party deployments) through Anthropic's public Mintlify docs MCP server. Returns ranked hits in the vendor's order with title, URL, page path, section anchor and a Markdown snippet. The search is semantic, so unusual queries can return loosely related hits. Claude Code docs (code.claude.com) and Claude Platform API docs (platform.claude.com) are separate sources.
- Instructions: To find which claude.com help page covers a claude.ai feature or admin task, then read it with get_page using the hit's `path` and `anchor` as `path` and `section`.
- Cost: 5 credits per call
- Capability file: [Search docs](https://firecrawl.dev/alexandria/agents/providers/claude-com/product-website/search_docs)

Accepted options:
- `limit` (number): Maximum hits, 1-10 (the server returns at most 10). Defaults to 10. Example: `10`
- `max_snippet_chars` (number): Cut each snippet to this many characters. Defaults to 1500. Example: `100`
- `query` (string, required): Search text, e.g. `MCP tunnels` or `share a plugin with my organization`. Example: `MCP tunnels`

Response schema example:
```json
{
  "count": 3,
  "observed_at_ms": 1792694709770,
  "query": "MCP tunnels",
  "results": [
    {
      "anchor": null,
      "markdown_url": "https://claude.com/docs/connectors/mcp-tunnels/overview.md",
      "path": "docs/connectors/mcp-tunnels/overview",
      "rank": 1,
      "snippet": "## Decide when to use an MCP tunnel\n\nUse a tunnel when the MCP server your organization wants to reach from Claude is only reachable inside your network, and your security policy rules out giving it a public endpoint or allowlisting Anthropic's IP ranges at your edge. Internal knowledge bases, ticke",
      "snippet_chars": 561,
      "snippet_truncated": true,
      "title": "MCP tunnels",
      "url": "https://claude.com/docs/connectors/mcp-tunnels/overview"
    },
    {
      "anchor": null,
      "markdown_url": "https://claude.com/docs/connectors/mcp-tunnels/troubleshooting.md",
      "path": "docs/connectors/mcp-tunnels/troubleshooting",
      "rank": 2,
      "snippet": "<Note>\n  MCP tunnels are in research preview and are available to organizations on the Claude Enterprise plan by request. To request access, [submit the MCP tunnels interest form](https://claude.com/form/mcp-tunnels) or contact your Anthropic account team.\n</Note>\n\nA request through an [MCP tunnel](",
      "snippet_chars": 1429,
      "snippet_truncated": true,
      "title": "Troubleshoot MCP tunnels",
      "url": "https://claude.com/docs/connectors/mcp-tunnels/troubleshooting"
    },
    {
      "anchor": null,
      "markdown_url": "https://claude.com/docs/connectors/mcp-tunnels/setup.md",
      "path": "docs/connectors/mcp-tunnels/setup",
      "rank": 3,
      "snippet": "## Remove a tunnel\n\nDecommission a tunnel when you no longer need it, or as the first steps of responding to a suspected compromise. Archiving a tunnel invalidates its token, detaches its domain, and is permanent.\n\n<Steps>\n  <Step title=\"Record the tunnel ID\">\n    <CodeGroup>\n      ```bash Helm them",
      "snippet_chars": 2269,
      "snippet_truncated": true,
      "title": "Set up an MCP tunnel",
      "url": "https://claude.com/docs/connectors/mcp-tunnels/setup"
    }
  ],
  "source_url": "https://claude.com/docs/mcp"
}
```

### Search resources

- Capability: `product-website/search_resources`
- Description: Search and list the claude.com resources library (articles and announcements, guides, webinars, videos) newest first, through the same JSON search the site's resources pages call. Filter by full-text `query`, `type`, `category`, `product` and `use_case`; each row has the type, title, URL, date, excerpt, category, products and reading time (webinars add session time, time zone and recording flags). Pages hold 12 rows; pass `page` or follow the continuation. The site serves at most 20 pages (240 rows) per search, so a `result_cap` warning tells you to narrow the filter when `total` exceeds that.
- Instructions: To find Claude announcements, best-practice articles, guides, webinars or videos about a topic or product, with dates, then read one with get_page (claude.com URLs).
- Cost: 5 credits per call
- Capability file: [Search resources](https://firecrawl.dev/alexandria/agents/providers/claude-com/product-website/search_resources)

Accepted options:
- `category` (string): Category slug. Example: `product-announcements`
- `page` (number): 1-based page of 12 rows. Defaults to 1. Example: `10`
- `product` (string): Product slug: claude-code, claude-cowork, claude-design, claude-enterprise, claude-managed-agents, claude-developer-platform, claude-security, claude-tag, claude-apps, claude-for-small-business. Pattern: ^[A-Za-z0-9-]+$. Example: `<product>`
- `query` (string): Full-text search, e.g. `subagents` or `prompt caching`. Example: `<query>`
- `type` (string): Resource type. Example: `article`
- `use_case` (string): Use-case slug, e.g. agents, coding, financial-services, legal, sales, security-and-admin. Pattern: ^[A-Za-z0-9-]+$. Example: `<use_case>`

Response schema example:
```json
{
  "category": null,
  "count": 4,
  "has_more": false,
  "observed_at_ms": 1792694709475,
  "page": 1,
  "page_size": 12,
  "product": null,
  "query": "subagents",
  "reachable_total": 4,
  "results": [
    {
      "categories": [
        "best-practices",
        "perspectives"
      ],
      "category": {
        "name": "Best practices",
        "slug": "best-practices"
      },
      "date": "2026-10-22",
      "duration": null,
      "event_date": null,
      "excerpt": "When building agents in Claude Platform, using fewer subagents in favor of progressively disclosed context and tools can improve quality while reducing cost and latency. Here’s when and how to migrate.",
      "external_url": null,
      "has_recording": null,
      "products": [
        {
          "name": "Claude Platform",
          "slug": "claude-developer-platform"
        }
      ],
      "read_time_minutes": 18,
      "recurring": null,
      "slug": "building-agents-when-to-fold-subagents-into-your-main-agent-loop",
      "time_zone": null,
      "title": "Building agents: When to fold subagents into your main agent loop",
      "type": "article",
      "url": "https://claude.com/resources/articles/building-agents-when-to-fold-subagents-into-your-main-agent-loop",
      "youtube_id": null
    },
    {
      "categories": [
        "best-practices"
      ],
      "category": {
        "name": "Best practices",
        "slug": "best-practices"
      },
      "date": "2026-04-07",
      "duration": null,
      "event_date": null,
      "excerpt": "A practical guide to Claude Code subagents: when they help, how to direct them, and the signals that tell you delegation is worth it.",
      "external_url": null,
      "has_recording": null,
      "products": [
        {
          "name": "Claude Code",
          "slug": "claude-code"
        }
      ],
      "read_time_minutes": 17,
      "recurring": null,
      "slug": "subagents-in-claude-code",
      "time_zone": null,
      "title": "How and when to use subagents in Claude Code",
      "type": "article",
      "url": "https://claude.com/resources/articles/subagents-in-claude-code",
      "youtube_id": null
    },
    {
      "categories": [
        "best-practices"
      ],
      "category": {
        "name": "Best practices",
        "slug": "best-practices"
      },
      "date": "2026-06-18",
      "duration": null,
      "event_date": null,
      "excerpt": null,
      "external_url": null,
      "has_recording": null,
      "products": [
        {
          "name": "Claude Code",
          "slug": "claude-code"
        }
      ],
      "read_time_minutes": 5,
      "recurring": null,
      "slug": "steering-claude-code-skills-hooks-rules-subagents-and-more",
      "time_zone": null,
      "title": "Steering Claude Code: when to use CLAUDE.md, skills, hooks, and subagents",
      "type": "article",
      "url": "https://claude.com/resources/articles/steering-claude-code-skills-hooks-rules-subagents-and-more",
      "youtube_id": null
    },
    {
      "categories": [
        "best-practices"
      ],
      "category": {
        "name": "Best practices",
        "slug": "best-practices"
      },
      "date": "2026-03-05",
      "duration": null,
      "event_date": null,
      "excerpt": "Skills are an increasingly powerful tool for creating custom AI workflows and agents, but where do they fit in the Claude stack? We explain what tool to use when - and how they all work together.",
      "external_url": null,
      "has_recording": null,
      "products": [
        {
          "name": "Claude apps",
          "slug": "claude-apps"
        },
        {
          "name": "Claude Platform",
          "slug": "claude-developer-platform"
        }
      ],
      "read_time_minutes": 16,
      "recurring": null,
      "slug": "skills-explained",
      "time_zone": null,
      "title": "Skills explained: How Skills compares to prompts, Projects, MCP, and subagents",
      "type": "article",
      "url": "https://claude.com/resources/articles/skills-explained",
      "youtube_id": null
    }
  ],
  "source_url": "https://claude.com/api/resources/search?query=subagents&types=article&language=en",
  "total": 4,
  "type": "article",
  "use_case": null
}
```