
Connects Claude to the Ensembl REST API for working with vertebrate genome data. Exposes seven core tools: stable ID lookups for genes, transcripts, and exons; gene symbol searches; cross-reference retrieval; sequence fetching; homology mappings; variation records; and the Variant Effect Predictor for analyzing genomic regions. Part of the Pipeworx gateway ecosystem, so you can either connect to just Ensembl or get access to their full catalog of 250+ data sources through a single endpoint. Useful when you need to annotate variants, trace gene homologs across species, or pull reference sequences without writing REST client code yourself.
Ensembl REST API MCP — vertebrate genomes, gene annotations, sequences, comparative genomics, variation. Keyless.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
lookup(id, expand?) — by stable id (gene/transcript/exon/translation)lookup_symbol(species, symbol) — gene by symbol within a speciesxrefs(species, symbol) — external cross-references for a gene symbolsequence(id, type?) — DNA / cDNA / CDS / protein sequencehomology(species, symbol_or_id, target_species?) — homology mappingsvariation(species, variant_id) — variation by name (e.g. "rs56116432")vep(species, region, allele) — Variant Effect Predictor (region: "9:22125504-22125504:1")xref_symbol(species, symbol) — symbol lookup (alias for /xrefs/symbol)https://rest.ensembl.org
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"ensembl": {
"url": "https://gateway.pipeworx.io/ensembl/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/ensembl/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 Ensembl data" })
The gateway picks the right tool and fills the arguments automatically.
MIT