Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-rcsb-pdb search for insulin binding proteins"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
RCSB Protein Data Bank MCP — 3-D structure metadata for ~225 k experimentally determined macromolecules. Keyless.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
search(query, return_type?, limit?) — text search across PDB
structure(pdb_id) — full entry record (experiment, ligands, polymer entities)
polymer_entity(pdb_id, entity_id) — single polymer entity (chain) metadata
ligand(pdb_id, ligand_id) — ligand record
assembly(pdb_id, assembly_id?) — biological assembly
summary(pdb_id) — short summary view
Related MCP server: Structural Biology MCP Server
Search: https://search.rcsb.org/rcsbsearch/v2/query
Data: https://data.rcsb.org/rest/v1/core/
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"rcsb-pdb": {
"url": "https://gateway.pipeworx.io/rcsb-pdb/mcp"
}
}
}tools/list at https://gateway.pipeworx.io/rcsb-pdb/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Rcsb Pdb data" })The gateway picks the right tool and fills the arguments automatically.
MIT
This server cannot be deployed
Protein research over UniProtKB — search by function, fetch curated records, map IDs, proteomes.
Search biomedical literature, get article details, find related articles, and explore MeSH terms
Link compounds to protein targets, rank bioactivity, and look up drug mechanisms and indications.
Search PubChem compounds, properties, safety data, bioactivity, and cross-references.
