AlphaFold Predicted Protein Structure for a UniProt Accession

alphafold/prediction

The AlphaFold predicted 3D structure record for one UniProt accession: mean pLDDT confidence and the share of residues in each confidence band, the protein sequence, gene, organism and model version, and the URLs of the model files (mmCIF, binary CIF, PDB), the predicted aligned error image and JSON, and the confidence JSON. Returns the first (full-length) model only, and URLs rather than the files themselves. AlphaFold Protein Structure Database data, CC-BY-4.0, served by Eden Engine; not an official EMBL-EBI product.

activeper callv1

Price

$0.0026 per call

You pay the price shown. If a call turns out to cost more than its quote, you pay the actual price, capped at twice the quote. No monthly minimum. Top-ups start at $5.

Data source

AlphaFold Protein Structure Database (EMBL-EBI)

AlphaFold DB data, CC-BY-4.0 (alphafold.ebi.ac.uk/download). Cite Fleming J. et al. AlphaFold Protein Structure Database and 3D-Beacons: New Data and Capabilities. J Mol Biol (2025) plus the structure's own publication. Served by Eden Engine; not an official EMBL-EBI product.

Use it

Five steps: search, inspect, learn, run, settle. No per-tool setup; your agent reaches this tool through the meta-tools it already has.

Connect once and your AI can find and run this tool, and any other it needs.

Install it Create an account

agent

// 1. search: find the tool
omnial_search({ query: "what you need" })

// 2. inspect: price and input schema
omnial_inspect({ tool: "alphafold/prediction" })

// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "alphafold/prediction" })

// 4. run: price the exact call first, then run it
omnial_execute({ tool: "alphafold/prediction", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "alphafold/prediction", input: { /* ... */ } })

// 5. settle: the call is charged when it finishes, nothing to do

Not connected yet? Point your MCP client at https://mcp.eden-engine.com/mcp, then copy a config for your client.

Pricing

Every charge this tool can incur.

Charge	Price
Per call	$0.0026

Updated: Oct 20, 2026

Input and output schemas

Input schema

input_schema.json

{
  "type": "object",
  "required": [
    "accession"
  ],
  "properties": {
    "accession": {
      "type": "string",
      "pattern": "^([OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2})$",
      "description": "A UniProt accession in capitals, for example P05067 (amyloid-beta precursor protein, human). Isoform suffixes such as P05067-2 are not accepted."
    }
  },
  "additionalProperties": false
}

Output schema

output_schema.json

{
  "type": "object",
  "required": [
    "entryId",
    "uniprotAccession",
    "globalMetricValue"
  ],
  "properties": {
    "gene": {
      "type": "string"
    },
    "taxId": {
      "type": "integer"
    },
    "cifUrl": {
      "type": "string",
      "description": "URL of the mmCIF model file."
    },
    "msaUrl": {
      "type": "string",
      "description": "URL of the multiple sequence alignment."
    },
    "pdbUrl": {
      "type": "string",
      "description": "URL of the PDB model file."
    },
    "bcifUrl": {
      "type": "string",
      "description": "URL of the binary CIF model file."
    },
    "entryId": {
      "type": "string",
      "description": "AlphaFold DB entry id, for example AF-P05067-F1."
    },
    "sequence": {
      "type": "string",
      "description": "The modelled amino-acid sequence."
    },
    "toolUsed": {
      "type": "string",
      "description": "The prediction pipeline."
    },
    "isComplex": {
      "type": "boolean"
    },
    "paeDocUrl": {
      "type": "string",
      "description": "URL of the predicted aligned error JSON."
    },
    "uniprotId": {
      "type": "string",
      "description": "UniProt entry name, for example A4_HUMAN."
    },
    "allVersions": {
      "type": "array",
      "items": {
        "type": "integer"
      }
    },
    "paeImageUrl": {
      "type": "string",
      "description": "URL of the predicted aligned error image."
    },
    "plddtDocUrl": {
      "type": "string",
      "description": "URL of the per-residue confidence JSON."
    },
    "sequenceEnd": {
      "type": "integer"
    },
    "latestVersion": {
      "type": "integer",
      "description": "Latest model version; file URLs carry it."
    },
    "modelEntityId": {
      "type": "string"
    },
    "sequenceStart": {
      "type": "integer"
    },
    "fractionPlddtLow": {
      "type": "number",
      "description": "Share with pLDDT 50 to 70."
    },
    "modelCreatedDate": {
      "type": "string"
    },
    "uniprotAccession": {
      "type": "string"
    },
    "globalMetricValue": {
      "type": "number",
      "description": "Mean pLDDT over the whole model, 0 to 100; higher is more confident."
    },
    "uniprotDescription": {
      "type": "string"
    },
    "fractionPlddtVeryLow": {
      "type": "number",
      "description": "Share of residues with pLDDT below 50."
    },
    "fractionPlddtVeryHigh": {
      "type": "number",
      "description": "Share with pLDDT above 90."
    },
    "fractionPlddtConfident": {
      "type": "number",
      "description": "Share with pLDDT 70 to 90."
    },
    "organismScientificName": {
      "type": "string"
    }
  },
  "description": "The first AlphaFold DB model record for the accession, in the provider's own field names.",
  "additionalProperties": true
}