bindingdb
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
@pipeworx/bindingdb
Measured protein/small-molecule binding affinities from BindingDB — Ki, Kd, IC50 and EC50 values in nM, each curated out of a published paper and carrying the PubMed ID it came from.
Part of Pipeworx — an MCP gateway connecting AI agents to 1863+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
Tools
bindingdb_ligands_by_uniprot(uniprot, cutoff?, limit?)— every ligand BindingDB has measured against a UniProt target, sorted by potency. Answers "what compounds bind this protein and how tightly".bindingdb_targets_by_smiles(smiles, similarity?, limit?)— the protein targets a compound (or a structurally similar one) has been measured against, with species. Answers compound-to-target and off-target questions.bindingdb_by_pdb(pdb, limit?)— affinities for the ligands associated with a PDB structure entry, linking a solved co-crystal to published potency.
Related MCP server: Structural Biology MCP Server
Auth
Keyless. No registration, no header.
Data sources
https://bindingdb.org/rest/getLigandsByUniprots —
uniprot=(comma-separated accessions),cutoff=(affinity in nM),response=application/json.https://bindingdb.org/rest/getTargetByCompound —
smiles=,cutoff=(Tanimoto similarity 0-1, NOT nM).https://bindingdb.org/rest/getLigandsByPDBs —
pdb=(one 4-character ID).
Things that will otherwise cost you an afternoon:
The base path is
/rest/, not/rwd/bind/rest/. The latter is in older docs and 404s from Tomcat with an HTML body./axis2/services/BDBService/...is also dead.The JSON envelope key does not match the endpoint name. All three respond under
getLindsByUniprotsResponse/getLindsByUniprotResponse/getLindsByPDBsResponse— note "Linds", a typo that is part of the contract. The compound endpoint additionally prefixes every field withbdb..getLigandsByPDBsanswers HTTP 500 with a SQL error in the body when it holds no data for that PDB ID — 2RH1 and 1ZZ1 both do this, 3EML works. That is an absent-data signal wearing a server-error costume; the pack says so rather than letting it read as an outage.Response size scales hard with
cutoff. P24941 at cutoff 1 is 387 KB, at 10 is 1.1 MB, at 100 is 2.2 MB; P00533 at 100 is 5 MB. The default here is 10.An affinity of
"0.000"means unreported, not infinitely potent. Values arrive as strings and may carry a qualifier (<1,>10000," 348000"), so the pack splits them intoaffinity_nm+qualifierand nulls the zeros rather than ranking them first.getLigandsByUniprotsreturns rows for related targets as well as the exact accession you asked for — thequeryfield on each row says which target the measurement is actually against.
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"bindingdb": {
"url": "https://gateway.pipeworx.io/bindingdb/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/bindingdb/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 1863+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/bindingdb_ligands_by_uniprot \
-H 'Content-Type: application/json' \
-d '{"uniprot":"P24941","cutoff":1,"limit":3}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/bindingdb_ligands_by_uniprot. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Run it from npm
@pipeworx/mcp-bindingdb is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with npx, and it forwards every call to the same
https://gateway.pipeworx.io/bindingdb/mcp endpoint shown above. It needs network access;
there is no offline mode.
{
"mcpServers": {
"bindingdb": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-bindingdb"]
}
}
}Without a key it calls anonymously, capped at 50 calls a day. A free account
raises that to 200 a day: get a key at https://pipeworx.io/signup and add
"env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry.
The key is sent as a Bearer token, the same way a hosted connection sends it,
so calls are metered and billed exactly as they are there.
It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to
also list ask_pipeworx and the other gateway-wide tools.
Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by
default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check
your Node version's documentation.
Using with ask_pipeworx
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 Bindingdb data" })The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Link compounds to protein targets, rank bioactivity, and look up drug mechanisms and indications.
Biomedical data: compounds, drug info, and molecular targets
Search PubChem compounds, properties, safety data, bioactivity, and cross-references.
Query STRING interactions, enrichment, annotations, homology, and PPI networks.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables searching, retrieving, and downloading protein structure data from the RCSB Protein Data Bank. Supports intelligent protein structure search, comprehensive data retrieval, and multiple file format downloads for bioinformatics research.3MIT
- FlicenseNot gradedqualityNot gradedmaintenanceEnables interaction with the RCSB Protein Data Bank to search, analyze, and visualize protein structures. It provides specialized tools for downloading coordinate files and performing structural modifications like residue mutations and metal atom replacements.-
- AlicenseNot gradedqualityBmaintenanceEnables querying and retrieving experimental protein structures from the RCSB Protein Data Bank, including text search, full entry records, polymer entities, ligands, and assemblies.195 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables access to the IUPHAR/BPS Guide to PHARMACOLOGY database for querying drug targets, ligands, and pharmacological data without API keys.471 npmMIT