
Connects Claude to Rhea, the expert-curated biochemical reactions database maintained by the Swiss Institute of Bioinformatics. Runs as a managed service through Pipeworx's gateway infrastructure, which means you get a stable HTTPS endpoint instead of running your own server. The standout feature is ask_pipeworx, which lets you query reaction data in plain English rather than wrestling with specific tool calls and parameters. Useful if you're building anything in computational biology, metabolic pathway analysis, or enzyme research where you need programmatic access to validated biochemical reaction data. The gateway approach also gives you the option to expand to 800+ other scientific data sources without additional setup.
Rhea MCP — expert-curated database of biochemical reactions.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
search_reactions | Search Rhea, the expert-curated database of biochemical reactions (the reaction reference used by UniProt and KEGG). Find enzyme/metabolic reactions by compound name, ChEBI id, EC number, or keyword and get the balanced plain-text reaction equation plus EC and ChEBI cross-references. Keyless. |
get_reaction | Fetch a single Rhea reaction by its Rhea id (e.g. "RHEA:14293" or "14293"). Returns the balanced plain-text equation plus EC number, ChEBI compound, UniProt enzyme and PubMed cross-references. Rhea is the expert-curated biochemical reaction reference used by UniProt and KEGG. Keyless. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"rhea": {
"url": "https://gateway.pipeworx.io/rhea/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/rhea/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 Rhea data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
curl -X POST https://gateway.pipeworx.io/v1/tools/search_reactions \
-H 'Content-Type: application/json' \
-d '{"query":"glucose"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/search_reactions. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.