
Connects Claude to MetaboLights, the European Bioinformatics Institute's open access repository for metabolomics experimental data and metadata. This is part of the Pipeworx gateway, which routes requests to 823+ data sources through a unified MCP interface. The server uses their ask_pipeworx pattern where you ask questions in plain English rather than calling specific tools. You'd reach for this when working with metabolic profiling studies, analyzing metabolite data, or exploring publicly available metabolomics experiments. Useful for researchers doing meta-analysis across studies or developers building tools that need programmatic access to metabolomics datasets without writing custom API clients.
MetaboLights MCP — EBI's metabolomics study repository.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
search_studies | Search EBI MetaboLights, the metabolomics (metabolite / small-molecule) study repository, by keyword — disease, metabolite, organism, or analytical technique (e.g. "diabetes", "glucose NMR", "Homo sapiens LC-MS"). Returns matching study accessions (e.g. MTBLS1) with name and a short description. |
get_study | Fetch metadata for a single MetaboLights study by its accession (e.g. "MTBLS1"): title, full description, and the organisms studied (species + tissue/part). Keyless. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"metabolights": {
"url": "https://gateway.pipeworx.io/metabolights/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/metabolights/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 Metabolights data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
curl -X POST https://gateway.pipeworx.io/v1/tools/metabolights_search_studies \
-H 'Content-Type: application/json' \
-d '{"query":"type 2 diabetes urine NMR"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/metabolights_search_studies. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.