--- type: "firecrawl-provider" description: "Experimentally determined 3D structures of proteins, nucleic acids and their complexes from the RCSB Protein Data Bank (wwPDB archive, CC0): search by text, organism, experimental method, resolution, release date, UniProt accession or bound ligand; full entry records with polymer entities, organisms, UniProt mappings, ligands, glycans, primary citation and coordinate download links; and Chemical Component Dictionary records for ligands with identifiers and cross-references (ChEMBL, DrugBank, PubChem, ChEBI). Uses the keyless RCSB Search and Data APIs." use_when: "Experimentally determined 3D structures of proteins, nucleic acids and their complexes from the RCSB Protein Data Bank (wwPDB archive, CC0): search by text, organism, experimental method, resolution, release date, UniProt accession or bound ligand; full entry records with polymer entities, organisms, UniProt mappings, ligands, glycans, primary citation and coordinate download links; and Chemical Component Dictionary records for ligands with identifiers and cross-references (ChEMBL, DrugBank, PubChem, ChEBI). Uses the keyless RCSB Search and Data APIs.\n\nExperimentally determined 3D structures of proteins, nucleic acids and their complexes from the RCSB Protein Data Bank (wwPDB archive, CC0): search by text, organism, experimental method, resolution, release date, UniProt accession or bound ligand; full entry records with polymer entities, organisms, UniProt mappings, ligands, glycans, primary citation and coordinate download links; and Chemical Component Dictionary records for ligands with identifiers and cross-references (ChEMBL, DrugBank, PubChem, ChEBI). Uses the keyless RCSB Search and Data APIs." categories: "Health" capabilities: 3 credits_per_call: 5 --- # RCSB Protein Data Bank on Firecrawl Alexandria Experimentally determined 3D structures of proteins, nucleic acids and their complexes from the RCSB Protein Data Bank (wwPDB archive, CC0): search by text, organism, experimental method, resolution, release date, UniProt accession or bound ligand; full entry records with polymer entities, organisms, UniProt mappings, ligands, glycans, primary citation and coordinate download links; and Chemical Component Dictionary records for ligands with identifiers and cross-references (ChEMBL, DrugBank, PubChem, ChEBI). Uses the keyless RCSB Search and Data APIs. - Categories: Health - Category index: [Health category](https://firecrawl.dev/alexandria/agents/categories/health) - Provider key: `rcsb-org` - Access: Firecrawl credits - Cost: 5 credits per call ## More - [Human guide](https://firecrawl.dev/app/alexandria/rcsb-org) - [OpenAPI spec](https://firecrawl.dev/alexandria/agents/providers/rcsb-org/openapi.json) ## Capabilities - [Search](https://firecrawl.dev/alexandria/agents/providers/rcsb-org/structures/search): Search the PDB archive of experimental structures through the RCSB Search API, then summarize each hit through the Data API: PDB ID, title, experimental method, resolution, release date, source organisms, UniProt accessions and search score. Combine full text with filters for organism (NCBI taxonomy lineage), experimental method, maximum resolution, release-date range, UniProt accession and bound ligand; filters are ANDed and at least one criterion is required. Offset-paginated through `next_offset`. Computed structure models (AlphaFold/ModelArchive) are excluded. An empty page is a valid result. - [Structure](https://firecrawl.dev/alexandria/agents/providers/rcsb-org/structures/structure): One PDB entry by ID or structure page URL through the RCSB Data API: title, keywords, experimental methods, resolution, deposit/release/revision dates and revision, authors, polymer entities (description, type, chains, sequence length, copies, weight, EC number, mutations, source organisms with NCBI taxonomy ids, UniProt accessions), ligands (Chemical Component id, name, formula, InChIKey, chains), branched entities (glycans), primary citation (DOI, PubMed ID) and download URLs (mmCIF, PDB format when available, BinaryCIF, FASTA). Unknown, obsolete and unreleased IDs fail as not_found; an obsolete ID names its superseding entry. - [Ligand](https://firecrawl.dev/alexandria/agents/providers/rcsb-org/ligands/ligand): One Chemical Component Dictionary entry (a ligand, ion, modified residue or monomer) by id or ligand page URL through the RCSB Data API: name, formula, formula weight, type, formal charge, release status and dates, atom count, InChI, InChIKey and SMILES, synonyms with their source, cross-references to ChEMBL, DrugBank, PubChem, ChEBI, CAS and CSD, and definition/ideal-coordinate download URLs. Unassigned ids fail as not_found. ## 1. Choose this provider when Experimentally determined 3D structures of proteins, nucleic acids and their complexes from the RCSB Protein Data Bank (wwPDB archive, CC0): search by text, organism, experimental method, resolution, release date, UniProt accession or bound ligand; full entry records with polymer entities, organisms, UniProt mappings, ligands, glycans, primary citation and coordinate download links; and Chemical Component Dictionary records for ligands with identifiers and cross-references (ChEMBL, DrugBank, PubChem, ChEBI). Uses the keyless RCSB Search and Data APIs. Experimentally determined 3D structures of proteins, nucleic acids and their complexes from the RCSB Protein Data Bank (wwPDB archive, CC0): search by text, organism, experimental method, resolution, release date, UniProt accession or bound ligand; full entry records with polymer entities, organisms, UniProt mappings, ligands, glycans, primary citation and coordinate download links; and Chemical Component Dictionary records for ligands with identifiers and cross-references (ChEMBL, DrugBank, PubChem, ChEBI). Uses the keyless RCSB Search and Data APIs. ## 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": "rcsb-org", "capability": "structures/search", "options": { "limit": 25, "query": "imatinib", "uniprot_accession": "P00519" } } ``` ## 3. Add provider options Use only the options needed for the task: - `experimental_method` (string): Combined experimental method label. Example: `X-ray` - `ligand` (string): Structures containing this Chemical Component Dictionary id as a non-polymer ligand, e.g. `STI` (imatinib), `HEM`, `ATP`. Look ids up with the `ligand` function. Pattern: ^[A-Za-z0-9]{1,5}$. Example: `` - `limit` (number): limit Example: `10` - `max_resolution` (number): Best resolution cutoff in ångströms (≤). Entries without a resolution (most NMR) are excluded when set. Example: `10` - `offset` (number): Number of hits to skip; pass the previous page's `next_offset`. Example: `0` - `organism` (string): Source organism scientific name, matched case-insensitively against the NCBI taxonomy lineage of every polymer entity, so `Escherichia coli` includes its strains and `Mammalia` includes every mammal. Example: `Escherichia coli` - `query` (string): Full-text search over titles, descriptions, keywords, organisms, ligand names, citations and annotations, e.g. `imatinib`, `spike glycoprotein`, `CRISPR Cas9`. Example: `` - `released_after` (string): Initial release on or after this date (YYYY-MM-DD). Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. Example: `` - `released_before` (string): Initial release on or before this date (YYYY-MM-DD). Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. Example: `` - `sort` (string): `relevance` (search score), `newest` (initial release date, newest first) or `resolution` (best first, entries without a resolution last). Example: `relevance` - `uniprot_accession` (string): Structures with a polymer entity mapped to this UniProtKB accession (SIFTS/RCSB reference sequence mapping), e.g. `P69905` for human hemoglobin alpha. Pattern: ^([OPQopq][0-9][A-Za-z0-9]{3}[0-9]|[A-NR-Za-nr-z][0-9]([A-Za-z][A-Za-z0-9]{2}[0-9]){1,2})$. Example: `P69905` ## 4. Request through your preferred interface ### JavaScript ```javascript const result = await firecrawl.scrape({ alexandria: { provider: "rcsb-org", capability: "structures/search", options: { limit: 25, query: "imatinib", uniprot_accession: "P00519", }, }, }); ``` ### Python ```python result = firecrawl.scrape_alexandria({ "provider": "rcsb-org", "capability": "structures/search", "options": { "limit": 25, "query": "imatinib", "uniprot_accession": "P00519" } }) ``` ### cURL ```sh curl https://api.firecrawl.dev/v2/scrape \ -H "Authorization: Bearer $FIRECRAWL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "alexandria": { "provider": "rcsb-org", "capability": "structures/search", "options": { "limit": 25, "query": "imatinib", "uniprot_accession": "P00519" } } }' ``` ### CLI ```sh firecrawl scrape 'rcsb-org/structures/search' \ --options '{"limit":25,"query":"imatinib","uniprot_accession":"P00519"}' ``` ### MCP Call the FCX MCP retrieve tool with this object: ```json { "provider": "rcsb-org", "capability": "structures/search", "options": { "limit": 25, "query": "imatinib", "uniprot_accession": "P00519" } } ``` Ask for only the returned fields needed by the task. ## 5. Full request shape ```json { "provider": "rcsb-org", "capability": "structures/search", "options": { "limit": 25, "query": "imatinib", "uniprot_accession": "P00519" } } ``` ## 6. Response data The response includes `success`, `provider`, `capability`, `creditsCost` and `data`. This example shows the provider payload in `data`: ```json { "license": "CC0-1.0", "limit": 25, "next_offset": null, "observed_at_ms": 1792447131657, "offset": 0, "results": [ { "experimental_method": "X-ray", "initial_release_date": "2022-04-27", "organisms": [ "Homo sapiens" ], "pdb_id": "7N9G", "resolution_angstrom": 2.2, "score": 0.7971516267184301, "title": "Crystal structure of the Abl 1b Kinase domain in complex with Dasatinib and Imatinib", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/7N9G" }, { "experimental_method": "X-ray", "initial_release_date": "2007-01-16", "organisms": [ "Homo sapiens" ], "pdb_id": "2HYY", "resolution_angstrom": 2.4, "score": 0.7550836593244821, "title": "Human Abl kinase domain in complex with imatinib (STI571, Glivec)", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/2HYY" }, { "experimental_method": "X-ray", "initial_release_date": "2011-03-09", "organisms": [ "Homo sapiens" ], "pdb_id": "3PYY", "resolution_angstrom": 1.85, "score": 0.7291328351654636, "title": "Discovery and Characterization of a Cell-Permeable, Small-molecule c-Abl Kinase Activator that Binds to the Myristoyl Binding Site", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/3PYY" }, { "experimental_method": "X-ray", "initial_release_date": "2019-03-13", "organisms": [ "Homo sapiens" ], "pdb_id": "6NPE", "resolution_angstrom": 2.15, "score": 0.7291328351654636, "title": "C-abl Kinase domain with the activator(cmpd6), 2-cyano-N-(4-(3,4-dichlorophenyl)thiazol-2-yl)acetamide", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/6NPE" }, { "experimental_method": "X-ray", "initial_release_date": "2019-03-13", "organisms": [ "Homo sapiens" ], "pdb_id": "6NPU", "resolution_angstrom": 2.33, "score": 0.7291328351654636, "title": "C-abl Kinase domain with the activator(cmpd29), N-(1-(3,4-dichlorophenyl)-4,5-dihydro-1H-pyrazol-3-yl)acetamide", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/6NPU" }, { "experimental_method": "X-ray", "initial_release_date": "2019-03-13", "organisms": [ "Homo sapiens" ], "pdb_id": "6NPV", "resolution_angstrom": 1.86, "score": 0.7291328351654636, "title": "C-abl Kinase domain with the activator(cmpd51), N-(1-(3,4-dichlorophenyl)-4-(2-hydroxyethyl)-4,5-dihydro-1H-pyrazol-3-yl)isonicotinamide", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/6NPV" }, { "experimental_method": "X-ray", "initial_release_date": "2006-01-24", "organisms": [ "Homo sapiens" ], "pdb_id": "2F4J", "resolution_angstrom": 1.91, "score": 0.6750003573657603, "title": "Structure of the Kinase Domain of an Imatinib-Resistant Abl Mutant in Complex with the Aurora Kinase Inhibitor VX-680", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/2F4J" }, { "experimental_method": "X-ray", "initial_release_date": "2006-11-21", "organisms": [ "Homo sapiens" ], "pdb_id": "2GQG", "resolution_angstrom": 2.4, "score": 0.619613473193679, "title": "X-ray Crystal Structure of Dasatinib (BMS-354825) Bound to Activated ABL Kinase Domain", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/2GQG" }, { "experimental_method": "X-ray", "initial_release_date": "2008-04-22", "organisms": [ "Homo sapiens" ], "pdb_id": "3CS9", "resolution_angstrom": 2.21, "score": 0.5665768890301535, "title": "Human ABL kinase in complex with nilotinib", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/3CS9" } ], "source_url": "https://search.rcsb.org/rcsbsearch/v2/query?json=%7B%22query%22%3A%7B%22logical_operator%22%3A%22and%22%2C%22nodes%22%3A%5B%7B%22parameters%22%3A%7B%22value%22%3A%22imatinib%22%7D%2C%22service%22%3A%22full_text%22%2C%22type%22%3A%22terminal%22%7D%2C%7B%22label%22%3A%22nested-attribute%22%2C%22logical_operator%22%3A%22and%22%2C%22nodes%22%3A%5B%7B%22parameters%22%3A%7B%22attribute%22%3A%22rcsb_polymer_entity_container_identifiers.reference_sequence_identifiers.database_accession%22%2C%22operator%22%3A%22exact_match%22%2C%22value%22%3A%22P00519%22%7D%2C%22service%22%3A%22text%22%2C%22type%22%3A%22terminal%22%7D%2C%7B%22parameters%22%3A%7B%22attribute%22%3A%22rcsb_polymer_entity_container_identifiers.reference_sequence_identifiers.database_name%22%2C%22operator%22%3A%22exact_match%22%2C%22value%22%3A%22UniProt%22%7D%2C%22service%22%3A%22text%22%2C%22type%22%3A%22terminal%22%7D%5D%2C%22type%22%3A%22group%22%7D%5D%2C%22type%22%3A%22group%22%7D%2C%22request_options%22%3A%7B%22paginate%22%3A%7B%22rows%22%3A25%2C%22start%22%3A0%7D%2C%22results_content_type%22%3A%5B%22experimental%22%5D%2C%22sort%22%3A%5B%7B%22direction%22%3A%22desc%22%2C%22sort_by%22%3A%22score%22%7D%5D%7D%2C%22return_type%22%3A%22entry%22%7D", "total_count": 9 } ``` ## API reference-derived contract The following capability contract is generated from the same normalized Alexandria API reference exposed in the API spec. ### Search - Capability: `structures/search` - Description: Search the PDB archive of experimental structures through the RCSB Search API, then summarize each hit through the Data API: PDB ID, title, experimental method, resolution, release date, source organisms, UniProt accessions and search score. Combine full text with filters for organism (NCBI taxonomy lineage), experimental method, maximum resolution, release-date range, UniProt accession and bound ligand; filters are ANDed and at least one criterion is required. Offset-paginated through `next_offset`. Computed structure models (AlphaFold/ModelArchive) are excluded. An empty page is a valid result. - Instructions: Find PDB entries for a protein, gene product, organism, ligand or method; join from UniProt with `uniprot_accession` or from a drug with `ligand`. Then call `structure` for chains, ligands, citation and download links. - Cost: 5 credits per call - Capability file: [Search](https://firecrawl.dev/alexandria/agents/providers/rcsb-org/structures/search) Accepted options: - `experimental_method` (string): Combined experimental method label. Example: `X-ray` - `ligand` (string): Structures containing this Chemical Component Dictionary id as a non-polymer ligand, e.g. `STI` (imatinib), `HEM`, `ATP`. Look ids up with the `ligand` function. Pattern: ^[A-Za-z0-9]{1,5}$. Example: `` - `limit` (number): limit Example: `10` - `max_resolution` (number): Best resolution cutoff in ångströms (≤). Entries without a resolution (most NMR) are excluded when set. Example: `10` - `offset` (number): Number of hits to skip; pass the previous page's `next_offset`. Example: `0` - `organism` (string): Source organism scientific name, matched case-insensitively against the NCBI taxonomy lineage of every polymer entity, so `Escherichia coli` includes its strains and `Mammalia` includes every mammal. Example: `Escherichia coli` - `query` (string): Full-text search over titles, descriptions, keywords, organisms, ligand names, citations and annotations, e.g. `imatinib`, `spike glycoprotein`, `CRISPR Cas9`. Example: `` - `released_after` (string): Initial release on or after this date (YYYY-MM-DD). Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. Example: `` - `released_before` (string): Initial release on or before this date (YYYY-MM-DD). Pattern: ^[0-9]{4}-[0-9]{2}-[0-9]{2}$. Example: `` - `sort` (string): `relevance` (search score), `newest` (initial release date, newest first) or `resolution` (best first, entries without a resolution last). Example: `relevance` - `uniprot_accession` (string): Structures with a polymer entity mapped to this UniProtKB accession (SIFTS/RCSB reference sequence mapping), e.g. `P69905` for human hemoglobin alpha. Pattern: ^([OPQopq][0-9][A-Za-z0-9]{3}[0-9]|[A-NR-Za-nr-z][0-9]([A-Za-z][A-Za-z0-9]{2}[0-9]){1,2})$. Example: `P69905` Response schema example: ```json { "license": "CC0-1.0", "limit": 25, "next_offset": null, "observed_at_ms": 1792447131657, "offset": 0, "results": [ { "experimental_method": "X-ray", "initial_release_date": "2022-04-27", "organisms": [ "Homo sapiens" ], "pdb_id": "7N9G", "resolution_angstrom": 2.2, "score": 0.7971516267184301, "title": "Crystal structure of the Abl 1b Kinase domain in complex with Dasatinib and Imatinib", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/7N9G" }, { "experimental_method": "X-ray", "initial_release_date": "2007-01-16", "organisms": [ "Homo sapiens" ], "pdb_id": "2HYY", "resolution_angstrom": 2.4, "score": 0.7550836593244821, "title": "Human Abl kinase domain in complex with imatinib (STI571, Glivec)", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/2HYY" }, { "experimental_method": "X-ray", "initial_release_date": "2011-03-09", "organisms": [ "Homo sapiens" ], "pdb_id": "3PYY", "resolution_angstrom": 1.85, "score": 0.7291328351654636, "title": "Discovery and Characterization of a Cell-Permeable, Small-molecule c-Abl Kinase Activator that Binds to the Myristoyl Binding Site", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/3PYY" }, { "experimental_method": "X-ray", "initial_release_date": "2019-03-13", "organisms": [ "Homo sapiens" ], "pdb_id": "6NPE", "resolution_angstrom": 2.15, "score": 0.7291328351654636, "title": "C-abl Kinase domain with the activator(cmpd6), 2-cyano-N-(4-(3,4-dichlorophenyl)thiazol-2-yl)acetamide", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/6NPE" }, { "experimental_method": "X-ray", "initial_release_date": "2019-03-13", "organisms": [ "Homo sapiens" ], "pdb_id": "6NPU", "resolution_angstrom": 2.33, "score": 0.7291328351654636, "title": "C-abl Kinase domain with the activator(cmpd29), N-(1-(3,4-dichlorophenyl)-4,5-dihydro-1H-pyrazol-3-yl)acetamide", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/6NPU" }, { "experimental_method": "X-ray", "initial_release_date": "2019-03-13", "organisms": [ "Homo sapiens" ], "pdb_id": "6NPV", "resolution_angstrom": 1.86, "score": 0.7291328351654636, "title": "C-abl Kinase domain with the activator(cmpd51), N-(1-(3,4-dichlorophenyl)-4-(2-hydroxyethyl)-4,5-dihydro-1H-pyrazol-3-yl)isonicotinamide", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/6NPV" }, { "experimental_method": "X-ray", "initial_release_date": "2006-01-24", "organisms": [ "Homo sapiens" ], "pdb_id": "2F4J", "resolution_angstrom": 1.91, "score": 0.6750003573657603, "title": "Structure of the Kinase Domain of an Imatinib-Resistant Abl Mutant in Complex with the Aurora Kinase Inhibitor VX-680", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/2F4J" }, { "experimental_method": "X-ray", "initial_release_date": "2006-11-21", "organisms": [ "Homo sapiens" ], "pdb_id": "2GQG", "resolution_angstrom": 2.4, "score": 0.619613473193679, "title": "X-ray Crystal Structure of Dasatinib (BMS-354825) Bound to Activated ABL Kinase Domain", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/2GQG" }, { "experimental_method": "X-ray", "initial_release_date": "2008-04-22", "organisms": [ "Homo sapiens" ], "pdb_id": "3CS9", "resolution_angstrom": 2.21, "score": 0.5665768890301535, "title": "Human ABL kinase in complex with nilotinib", "uniprot_accessions": [ "P00519" ], "url": "https://www.rcsb.org/structure/3CS9" } ], "source_url": "https://search.rcsb.org/rcsbsearch/v2/query?json=%7B%22query%22%3A%7B%22logical_operator%22%3A%22and%22%2C%22nodes%22%3A%5B%7B%22parameters%22%3A%7B%22value%22%3A%22imatinib%22%7D%2C%22service%22%3A%22full_text%22%2C%22type%22%3A%22terminal%22%7D%2C%7B%22label%22%3A%22nested-attribute%22%2C%22logical_operator%22%3A%22and%22%2C%22nodes%22%3A%5B%7B%22parameters%22%3A%7B%22attribute%22%3A%22rcsb_polymer_entity_container_identifiers.reference_sequence_identifiers.database_accession%22%2C%22operator%22%3A%22exact_match%22%2C%22value%22%3A%22P00519%22%7D%2C%22service%22%3A%22text%22%2C%22type%22%3A%22terminal%22%7D%2C%7B%22parameters%22%3A%7B%22attribute%22%3A%22rcsb_polymer_entity_container_identifiers.reference_sequence_identifiers.database_name%22%2C%22operator%22%3A%22exact_match%22%2C%22value%22%3A%22UniProt%22%7D%2C%22service%22%3A%22text%22%2C%22type%22%3A%22terminal%22%7D%5D%2C%22type%22%3A%22group%22%7D%5D%2C%22type%22%3A%22group%22%7D%2C%22request_options%22%3A%7B%22paginate%22%3A%7B%22rows%22%3A25%2C%22start%22%3A0%7D%2C%22results_content_type%22%3A%5B%22experimental%22%5D%2C%22sort%22%3A%5B%7B%22direction%22%3A%22desc%22%2C%22sort_by%22%3A%22score%22%7D%5D%7D%2C%22return_type%22%3A%22entry%22%7D", "total_count": 9 } ``` ### Structure - Capability: `structures/structure` - Description: One PDB entry by ID or structure page URL through the RCSB Data API: title, keywords, experimental methods, resolution, deposit/release/revision dates and revision, authors, polymer entities (description, type, chains, sequence length, copies, weight, EC number, mutations, source organisms with NCBI taxonomy ids, UniProt accessions), ligands (Chemical Component id, name, formula, InChIKey, chains), branched entities (glycans), primary citation (DOI, PubMed ID) and download URLs (mmCIF, PDB format when available, BinaryCIF, FASTA). Unknown, obsolete and unreleased IDs fail as not_found; an obsolete ID names its superseding entry. - Instructions: Read the full record of a PDB ID found with `search`, in a paper or on rcsb.org, e.g. to get its UniProt mappings, ligands, citation or coordinate files. - Cost: 5 credits per call - Capability file: [Structure](https://firecrawl.dev/alexandria/agents/providers/rcsb-org/structures/structure) Accepted options: - `pdb_id` (string): PDB ID, four characters (`4HHB`) or the extended form (`pdb_00004hhb`). Give this or `url`. Pattern: ^([0-9][A-Za-z0-9]{3}|[Pp][Dd][Bb]_[A-Za-z0-9]{8})$. Example: `4HHB` - `url` (string): Structure page URL, e.g. https://www.rcsb.org/structure/4HHB. Give this or `pdb_id`. Example: `pdb_id` Response schema example: ```json { "authors": [ "Fermi, G.", "Perutz, M.F." ], "branched_entities": [], "deposit_date": "1984-03-07", "deposited_atom_count": 4779, "doi": "10.2210/pdb4hhb/pdb", "downloads": { "bcif": "https://models.rcsb.org/4HHB.bcif", "fasta": "https://www.rcsb.org/fasta/entry/4HHB", "mmcif": "https://files.rcsb.org/download/4HHB.cif", "mmcif_gz": "https://files.rcsb.org/download/4HHB.cif.gz", "pdb": "https://files.rcsb.org/download/4HHB.pdb" }, "experimental_method": "X-ray", "experimental_methods": [ "X-RAY DIFFRACTION" ], "extended_id": "pdb_00004hhb", "initial_release_date": "1984-07-17", "keywords": "OXYGEN TRANSPORT", "license": "CC0-1.0", "ligands": [ { "chains": [ "A", "B", "C", "D" ], "comp_id": "HEM", "copies": 4, "entity_id": "3", "formula": "C34 H32 Fe N4 O4", "formula_weight_da": 616.487, "inchikey": "KABFMIBPWCXCRK-RGGAHWMASA-L", "name": "PROTOPORPHYRIN IX CONTAINING FE", "url": "https://www.rcsb.org/ligand/HEM" }, { "chains": [ "B", "D" ], "comp_id": "PO4", "copies": 2, "entity_id": "4", "formula": "O4 P", "formula_weight_da": 94.971, "inchikey": "NBIIXXVUZAFLBC-UHFFFAOYSA-K", "name": "PHOSPHATE ION", "url": "https://www.rcsb.org/ligand/PO4" } ], "molecular_weight_kda": 64.74, "observed_at_ms": 1792447131659, "pdb_id": "4HHB", "polymer_entities": [ { "chains": [ "A", "C" ], "copies": 2, "description": "Hemoglobin subunit alpha", "ec_number": null, "entity_id": "1", "molecular_weight_kda": 15.15, "mutation": null, "organisms": [ { "scientific_name": "Homo sapiens", "taxonomy_id": 9606 } ], "polymer_type": "Protein", "sequence_length": 141, "uniprot_accessions": [ "P69905" ] }, { "chains": [ "B", "D" ], "copies": 2, "description": "Hemoglobin subunit beta", "ec_number": null, "entity_id": "2", "molecular_weight_kda": 15.89, "mutation": null, "organisms": [ { "scientific_name": "Homo sapiens", "taxonomy_id": 9606 } ], "polymer_type": "Protein", "sequence_length": 146, "uniprot_accessions": [ "P68871" ] } ], "primary_citation": { "authors": [ "Fermi, G.", "Perutz, M.F.", "Shaanan, B.", "Fourme, R." ], "doi": "10.1016/0022-2836(84)90472-8", "journal": "J.Mol.Biol.", "page_first": "159", "page_last": "174", "pubmed_id": "6726807", "title": "The crystal structure of human deoxyhaemoglobin at 1.74 A resolution", "volume": "175", "year": 1984 }, "resolution_angstrom": 1.74, "revision": "4.3", "revision_date": "2026-08-12", "source_url": "https://www.rcsb.org/structure/4HHB", "status": "REL", "title": "THE CRYSTAL STRUCTURE OF HUMAN DEOXYHAEMOGLOBIN AT 1.74 ANGSTROMS RESOLUTION" } ``` ### Ligand - Capability: `ligands/ligand` - Description: One Chemical Component Dictionary entry (a ligand, ion, modified residue or monomer) by id or ligand page URL through the RCSB Data API: name, formula, formula weight, type, formal charge, release status and dates, atom count, InChI, InChIKey and SMILES, synonyms with their source, cross-references to ChEMBL, DrugBank, PubChem, ChEBI, CAS and CSD, and definition/ideal-coordinate download URLs. Unassigned ids fail as not_found. - Instructions: Identify a ligand code seen in a PDB entry (`STI`, `HEM`) or map it to ChEMBL/DrugBank/PubChem; then `search` with `ligand` to list structures that contain it. - Cost: 5 credits per call - Capability file: [Ligand](https://firecrawl.dev/alexandria/agents/providers/rcsb-org/ligands/ligand) Accepted options: - `comp_id` (string): Chemical Component Dictionary id, 1 to 5 letters or digits (`STI`, `HEM`, `ATP`). Give this or `url`. Pattern: ^[A-Za-z0-9]{1,5}$. Example: `` - `url` (string): Ligand page URL, e.g. https://www.rcsb.org/ligand/STI. Give this or `comp_id`. Example: `comp_id` Response schema example: ```json { "atom_count": 68, "comp_id": "STI", "cross_references": [ { "accession": "DB00619", "resource": "DrugBank" }, { "accession": "XAVTOF02", "resource": "CCDC/CSD" }, { "accession": "XAVTOF03", "resource": "CCDC/CSD" }, { "accession": "XEJLUW", "resource": "CCDC/CSD" }, { "accession": "XAVTOF", "resource": "CCDC/CSD" }, { "accession": "DUNTIQ", "resource": "CCDC/CSD" }, { "accession": "XAVTOF04", "resource": "CCDC/CSD" }, { "accession": "CAPVAU", "resource": "CCDC/CSD" }, { "accession": "CAPVEY", "resource": "CCDC/CSD" }, { "accession": "CAPVOI", "resource": "CCDC/CSD" }, { "accession": "5291", "resource": "PubChem" }, { "accession": "152459-95-5", "resource": "CAS" }, { "accession": "CHEBI:45783", "resource": "ChEBI" }, { "accession": "CHEMBL941", "resource": "ChEMBL" }, { "accession": "CHEMBL941", "resource": "Pharos" } ], "downloads": { "definition_cif": "https://files.rcsb.org/ligands/download/STI.cif", "ideal_sdf": "https://files.rcsb.org/ligands/download/STI_ideal.sdf" }, "formal_charge": 0, "formula": "C29 H31 N7 O", "formula_weight_da": 493.603, "inchi": "InChI=1S/C29H31N7O/c1-21-5-10-25(18-27(21)34-29-31-13-11-26(33-29)24-4-3-12-30-19-24)32-28(37)23-8-6-22(7-9-23)20-36-16-14-35(2)15-17-36/h3-13,18-19H,14-17,20H2,1-2H3,(H,32,37)(H,31,33,34)", "inchikey": "KTUFNOKKBVMGRW-UHFFFAOYSA-N", "initial_release_date": "2001-04-18", "license": "CC0-1.0", "name": "4-(4-METHYL-PIPERAZIN-1-YLMETHYL)-N-[4-METHYL-3-(4-PYRIDIN-3-YL-PYRIMIDIN-2-YLAMINO)-PHENYL]-BENZAMIDE", "observed_at_ms": 1792447131659, "release_status": "REL", "revision_date": "2020-06-05", "smiles": "Cc1ccc(cc1Nc2nccc(n2)c3cccnc3)NC(=O)c4ccc(cc4)CN5CCN(CC5)C", "smiles_stereo": "Cc1ccc(cc1Nc2nccc(n2)c3cccnc3)NC(=O)c4ccc(cc4)CN5CCN(CC5)C", "source_url": "https://www.rcsb.org/ligand/STI", "synonyms": [ { "name": "4-(4-METHYL-PIPERAZIN-1-YLMETHYL)-N-[4-METHYL-3-(4-PYRIDIN-3-YL-PYRIMIDIN-2-YLAMINO)-PHENYL]-BENZAMIDE", "source": "PDB Reference Data", "type": "Preferred Name" }, { "name": "STI-571", "source": "PDB Reference Data", "type": "Synonym" }, { "name": "IMATINIB", "source": "PDB Reference Data", "type": "Synonym" }, { "name": "4-[(4-methylpiperazin-1-yl)methyl]-N-{4-methyl-3-[(4-pyridin-3-ylpyrimidin-2-yl)amino]phenyl}benzamide", "source": "ACDLabs", "type": "Systematic Name" }, { "name": "4-[(4-methylpiperazin-1-yl)methyl]-N-[4-methyl-3-[(4-pyridin-3-ylpyrimidin-2-yl)amino]phenyl]benzamide", "source": "OpenEye OEToolkits", "type": "Systematic Name" }, { "name": "α-(4-methyl-1-piperazinyl)-3'-((4-(3-pyridyl)-2-pyrimidinyl)amino)-p-toluidide", "source": "DrugBank", "type": "Synonym" }, { "name": "Imatinib", "source": "DrugBank", "type": "Synonym" }, { "name": "Imatinib mesylate", "source": "DrugBank", "type": "Synonym" }, { "name": "Imatinibum", "source": "DrugBank", "type": "Synonym" } ], "type": "non-polymer" } ```