AlphaFold Protein Structure Database
alphafold.ebi.ac.uk
EMBL-EBI and Google DeepMind's AlphaFold Protein Structure Database: predicted three-dimensional structures for over 200 million proteins, searchable by UniProt accession, AlphaFold model id, amino-acid sequence or sequence MD5, returning per-model confidence (pLDDT) and interface scores, downloadable mmCIF/PDB/BCIF/PAE files, predicted protein complexes, and AlphaMissense pathogenicity predictions for every possible missense variant of a human protein.
GET /v1/data/alphafold/alphamissense1Request
A human UniProtKB accession; AlphaMissense covers the human proteome only (a non-human accession such as P02769 returns 404). The annotation type is pinned to MUTAGEN, the only value the upstream enum accepts.
curl "https://api.fastcrw.com/v1/data/alphafold/alphamissense?qualifier=P04637" \ -H "Authorization: Bearer $FASTCRW_API_KEY"
2Response example
A sample shape. Press Run to see live data from AlphaFold Protein Structure Database.
| type | description | source_name | source_url | evidence | residues | regions |
|---|---|---|---|---|---|---|
| MUTAGEN | AM score | AFDB | https://alphafold.ebi.ac.uk/files/AF-P04637-F1-aa-substitutions.csv | COMPUTATIONAL/PREDICTED | [1,2,3,4,5,6,7,8,9,10,"… 383 more items"] | [{"start":1,"end":1,"annotation_value":"0.4911","unit":null},{"start":2,"end":2,"annotation_value":"0.2725","unit":null},{"start":3,"end":3,"annotation_value":"0.1885","unit":null},{"start":4,"end":4,"annotation_value":"0.109","unit":null},{"start":5,"end":5,"annotation_value":"0.1159","unit":null},{"start":6,"end":6,"annotation_value":"0.1361","unit":null},{"start":7,"end":7,"annotation_value":"0.1786","unit":null},{"start":8,"end":8,"annotation_value":"0.0963","unit":null},{"start":9,"end":9,"annotation_value":"0.1217","unit":null},{"start":10,"end":10,"annotation_value":"0.1369","unit":null},"… 383 more items"] |
Attribution: AlphaFold Protein Structure Database (EMBL-EBI and Google DeepMind), CC BY 4.0. AlphaFold Data Copyright (2022) DeepMind Technologies Limited; AlphaMissense Copyright (2023) DeepMind Technologies Limited.
Licence: The AlphaFold Protein Structure Database states under "Licence and attributions" on alphafold.ebi.ac.uk: "Data is available for academic and commercial use, under a CC-BY-4.0 licence." (linking https://creativecommons.org/licenses/by/4.0/). The same section continues: "EMBL-EBI expects attribution (e.g., in publications, services, or products) for any of its online services, databases, or software in accordance with good scientific practice." and "If you use this resource, please cite the following papers: Bertoni D. et al. AlphaFold Protein Structure Database 2025: a redesigned interface and updated structural coverage, Nucleic Acids Research, (2025)", with the caveat "Note: A given structure may be associated with further publications. For authoritative information regarding the relevant publication(s), please consult the dataset collection or the structure metadata provided on the entry page." Copyright notices listed there: "AlphaFold Data Copyright (2022) DeepMind Technologies Limited.", "AlphaMissense Copyright (2023) DeepMind Technologies Limited." and, for third-party contributed sets served through the same API, "Kinetoplastid data copyright (2025) Wheeler Lab", "AllTheBacteria data copyright (2025) AllTheBacteria Consortium", "A BFVD Data Copyright (2025) The BFVD Development Team", "Viro3D dataset (2025)" and "VAD dataset (2026)" - all of which the page places under the same blanket CC-BY-4.0 statement, each asking for its own citation. AlphaMissense predictions additionally ask: "If you use data from AlphaMissense in your work, please cite the following paper: Cheng, J et al. Accurate proteome-wide missense variant effect prediction with AlphaMissense. Science (2023)." CC BY 4.0 permits commercial use and redistribution provided attribution is given, so both are set true.
Ask with this source
A prompt for your agent that names this source and how to call it through the crw MCP.
AlphaMissense pathogenicity per residue
Use AlphaFold Protein Structure Database (alphafold) from fastCRW Pergamon, capability "AlphaMissense pathogenicity per residue" (alphamissense). You hold a human UniProt accession and want a per-residue map of how damaging mutations there are predicted to be - to rank hotspots along a sequence, not to look up one variant. Example options: qualifier=P04637. Use the crw MCP tools: crw_find_data to confirm the source and its options, then crw_get_data with provider "alphafold" and capability "alphamissense". Tell me the credits used and cite the licence from the response. If the crw MCP tools are missing, install them with: npx -y crw-mcp install --api-key <your fastCRW API key>
Structures for a sequence MD5
Use AlphaFold Protein Structure Database (alphafold) from fastCRW Pergamon, capability "Structures for a sequence MD5" (checksum-summary). You already have the MD5 checksum of a protein sequence - from a prediction record's sequenceChecksum, or computed locally - and want its structures without putting the whole sequence in the URL. Example options: id=6077c452d1dc6151040b2b179e2294c7, rows=50. Use the crw MCP tools: crw_find_data to confirm the source and its options, then crw_get_data with provider "alphafold" and capability "checksum-summary". Tell me the credits used and cite the licence from the response. If the crw MCP tools are missing, install them with: npx -y crw-mcp install --api-key <your fastCRW API key>
Predicted complexes containing a protein
Use AlphaFold Protein Structure Database (alphafold) from fastCRW Pergamon, capability "Predicted complexes containing a protein" (complexes). You want to know which predicted protein-protein complexes a protein takes part in, and how confident the predicted interface is, rather than its monomer structure. Example options: qualifier=P69905. Use the crw MCP tools: crw_find_data to confirm the source and its options, then crw_get_data with provider "alphafold" and capability "complexes". Tell me the credits used and cite the licence from the response. If the crw MCP tools are missing, install them with: npx -y crw-mcp install --api-key <your fastCRW API key>
Structure predictions for a protein
Use AlphaFold Protein Structure Database (alphafold) from fastCRW Pergamon, capability "Structure predictions for a protein" (prediction). You have a UniProt accession or an AlphaFold model id and want that protein's predicted structure records, confidence scores and file download links - the default starting point for this source. Example options: qualifier=P69905, sequence_checksum=6077c452d1dc6151040b2b179e2294c7, include_complexes=true. Use the crw MCP tools: crw_find_data to confirm the source and its options, then crw_get_data with provider "alphafold" and capability "prediction". Tell me the credits used and cite the licence from the response. If the crw MCP tools are missing, install them with: npx -y crw-mcp install --api-key <your fastCRW API key>