AlphaFold MCP Server

A comprehensive Model Context Protocol server for accessing AlphaFold Protein Structure Database with advanced protein structure prediction tools

Local serverstdioTypeScript

What is the AlphaFold MCP server?

AlphaFold MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. A comprehensive Model Context Protocol server for accessing AlphaFold Protein Structure Database with advanced protein structure prediction tools.

What you get

This MCP server enables seamless integration with AlphaFold's vast collection of protein structure predictions, offering tools for structure retrieval, confidence analysis, batch processing, and visualization preparation. Perfect for researchers, bioinformaticians, and structural biologists working with predicted protein structures.

What the assistant can call

Once AlphaFold is connected, these are the calls the assistant has available:

  • Multi — format Downloads**: Support for PDB, CIF, BCIF, and JSON formats
  • Metadata — Prediction versions, dates, and quality information
  • Cross-references — Links to other databases and resources
  • get_structure — Retrieve AlphaFold structure prediction for a specific UniProt ID
  • download_structure — The download_structure tool exposed by this server
  • check_availability — Check if AlphaFold structure prediction is available for a UniProt ID
  • search_structures — Search for available AlphaFold structures by protein name or gene
  • list_by_organism — The list_by_organism tool exposed by this server
  • get_organism_stats — The get_organism_stats tool exposed by this server
  • get_confidence_scores — Get per-residue confidence scores for a structure prediction
  • analyze_confidence_regions — Analyze confidence score distribution and identify high/low confidence regions
  • get_prediction_metadata — Get metadata about the prediction including version, date, and quality metrics

Setting it up

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.

Choosing this one

Among the database access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. AlphaFold's toolset — Multi, Metadata, Cross-references and 11 more — is a fair guide to whether it matches your workflow. It is maintained by Augmented-Nature; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch AlphaFold.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the alphafold mcp server does with a few real requests.

Available tools

ToolWhat it does
Multiformat Downloads**: Support for PDB, CIF, BCIF, and JSON formats
MetadataPrediction versions, dates, and quality information
Cross-referencesLinks to other databases and resources
get_structureRetrieve AlphaFold structure prediction for a specific UniProt ID.
download_structureThe download_structure tool exposed by this server.
check_availabilityCheck if AlphaFold structure prediction is available for a UniProt ID.
search_structuresSearch for available AlphaFold structures by protein name or gene.
list_by_organismThe list_by_organism tool exposed by this server.
get_organism_statsThe get_organism_stats tool exposed by this server.
get_confidence_scoresGet per-residue confidence scores for a structure prediction.
analyze_confidence_regionsAnalyze confidence score distribution and identify high/low confidence regions.
get_prediction_metadataGet metadata about the prediction including version, date, and quality metrics.
batch_structure_infoGet structure information for multiple proteins simultaneously.
batch_downloadThe batch_download tool exposed by this server.

Example prompts to try

  • Use AlphaFold to Multi.
  • Use AlphaFold to Metadata.
  • Use AlphaFold to Cross-references.

Frequently asked questions

It connects AlphaFold to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (Multi, Metadata, Cross-references, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with AlphaFold directly.