bindingdb_ligands_by_uniprot
Pack: bindingdb · Endpoint: https://gateway.pipeworx.io/bindingdb/mcp
No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/bindingdb_ligands_by_uniprot for the schema, then POST the same URL with its arguments for the data.
Measured binding affinities (Ki, Kd, IC50, EC50 in nM) for every ligand BindingDB has curated against a UniProt target, each with the PubMed ID of the paper it was measured in. AUTHORITATIVE for “what compounds bind this protein and how tightly” — this is experimental medicinal-chemistry data, not a prediction or a web summary. Pass one or more UniProt accessions (e.g. P24941 for CDK2).
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
uniprot | string | yes | UniProt accession, or several comma-separated (e.g. “P24941” or “P24941,P00533”) |
cutoff | number | no | Affinity cutoff in nM — only measurements at or below this are returned. Default 10. Raising it enlarges the upstream response substantially (100 nM on a well-studied kinase is several MB). |
limit | number | no | Max rows to return, 1-500 (default 50). Sorted by potency. |
Example call
Arguments
{
"uniprot": "P24941",
"cutoff": 1,
"limit": 3
}
curl
curl -X POST https://gateway.pipeworx.io/bindingdb/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"bindingdb_ligands_by_uniprot","arguments":{"uniprot":"P24941","cutoff":1,"limit":3}}}'
TypeScript (@pipeworx/sdk)
import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();
const result = await pipeworx.call('bindingdb_ligands_by_uniprot', {
"uniprot": "P24941",
"cutoff": 1,
"limit": 3
});
Connect
Add this to your MCP client config, or use one-click install buttons:
{
"mcpServers": {
"bindingdb": {
"url": "https://gateway.pipeworx.io/bindingdb/mcp"
}
}
}
See Getting Started for client-specific install steps.