protein_get_structure

MCP tool from Protein MCP Server by cyanheads

Fetch metadata and coordinate-file URLs by ID — experimental (PDB), predicted (AlphaFold), or best-available — with batch partial success and optional coordinate inlining.

How to use it

protein_get_structure is exposed by the Protein MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the protein_get_structure tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Protein MCP Server

$bunx @cyanheads/protein-mcp-server@latest

FULL PROTEIN MCP SERVER LISTING

Other tools in Protein MCP Server (6)

protein_analyze_collection

Profile the PDB into distributions and trends with server-side facets — counts, histograms, timelines, and cross-tabs.

protein_compare_structures

Structurally align multiple structures (TM-align / jFATCAT) to a reference or as a full pairwise matrix.

protein_find_similar

Find sequence homologs (RCSB mmseqs2) or fold homologs (Foldseek) from a sequence, PDB ID, or UniProt accession.

protein_get_annotations

Fetch UniProt features and natural variants plus InterPro domain/family memberships with GO terms.

protein_search_structures

Search experimental and predicted structures by free text, sequence, or organism/method/resolution filters, with optional facet breakdowns.

protein_track_ligands

Resolve ligand names/formulas to component IDs, find structures containing a ligand, or map binding-site residues.