What it does
The server gives MCP-compatible clients access to protein structure and annotation information drawn from two sources: experimentally determined structures in the PDB, and predicted models from AlphaFold. Its publisher describes it as federating these sources, so a single server covers both kinds of model.
It would be relevant to someone building or running a tool-using AI workflow that needs protein structure lookups, for example when working on molecular or bioinformatics tasks and wanting an assistant to fetch structure data directly rather than through manual database searches.
The publisher's documentation was not available in the facts provided, so setup steps, required credentials and the exact set of tools exposed are not described here. The repository is hosted on GitHub.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 15 Nov 2026 · its page on the source
io.github.cyanheads/protein-mcp-server
Federated protein structure & annotation across experimental (PDB) and predicted (AlphaFold) models.
v0.9.1As shown on registry.modelcontextprotocol.io when we last read it