
This server wraps the MyGene.info API, giving you programmatic access to gene annotations pulled from NCBI, Ensembl, UniProt, KEGG, and OMIM. You get five tools: full-text gene search, single gene lookups, batch queries, metadata about data sources and releases, and species taxonomy retrieval. It's hosted through Pipeworx's gateway, so no local setup needed. Reach for this when you're building genomics workflows and need to resolve gene IDs, query gene functions, or pull cross-referenced annotations without manually hitting multiple bioinformatics databases. The ask_pipeworx wrapper lets you query in natural language if you prefer that to direct tool calls.
MyGene.info MCP — gene annotation service from BioThings (NCBI, Ensembl, UniProt, KEGG, OMIM, etc., joined per gene). Keyless.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
query(query, species?, fields?, size?, sort?) — full-text gene querygene(gene_id, fields?, species?) — annotations for a gene id (Entrez or Ensembl)query_many(ids, scopes?, species?, fields?) — batch lookupmetadata() — release / source metadatataxonomy(species) — species taxonomy infohttps://mygene.info/v3/
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"mygene-info": {
"url": "https://gateway.pipeworx.io/mygene-info/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/mygene-info/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 Mygene Info data" })
The gateway picks the right tool and fills the arguments automatically.
MIT