Chembl MCP server

@pipeworx/chembl

ChEMBL MCP — drug-discovery database from EBI: bioactive molecules, drug targets, mechanism of action, clinical phases. Keyless.

Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.

Tools

from a drug name. Searches every molecule form the name matched (base + salts) in one mechanism query, so drugs whose pharmacology is curated on the salt still resolve — e.g. metformin's two mechanisms live on CHEMBL1703 (METFORMIN HYDROCHLORIDE), while the best name match CHEMBL1431 (METFORMIN) has none. Returns action_type, mechanism text, named target + organism, the form each mechanism was recorded on, and PubMed refs.

• search(query, type?, limit?) — search molecules / targets / assays / docs
• molecule(chembl_id) — full molecule record
• target(chembl_id) — target (protein) record
• mechanism(chembl_id) — raw mechanism rows for one exact molecule ID
• chemblmechanism(drug | moleculechembl_id, candidates?, limit?) — mechanism of action

• activities(moleculechemblid?, targetchemblid?, limit?) — activity records
• drugindications(moleculechemblid?, meshid?, limit?) — disease indications

Data source

https://www.ebi.ac.uk/chembl/api/data/

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "chembl": {
      "url": "https://gateway.pipeworx.io/chembl/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/chembl/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, 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 1679+ 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/chembl_search \
  -H 'Content-Type: application/json' \
  -d '{"query":"aspirin"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/chemblsearch. Find one: POST https://gateway.pipeworx.io/v1/tools/searchpacks with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "chembl": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-chembl"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-chembl

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Shortened. The full README is on GitHub.