Mgnify MCP server

@pipeworx/mgnify

MGnify (EMBL-EBI) — public metagenomics studies, the controlled biome vocabulary they are classified under, and the ~57,000 MAGs and isolate genomes in MGnify's species-level genome catalogues, with completeness, contamination and GTDB taxonomy for each.

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

Tools

by free text and/or biome, each with its ENA project accessions.

• mgnifysearchstudies(search?, biome_lineage?, limit?) — microbiome studies

catalogues, with CheckM completeness/contamination, N50, GC, origin and ENA/NCBI cross-references.

• mgnify_study(accession) — one MGYS study in full.
• mgnifygenomes(search?, catalogueid?, taxon_lineage?, limit?) — the genome

The exact lineage strings are not guessable; look them up here first.

• mgnifybiomes(lineageprefix?, limit?) — the ~492-lineage biome vocabulary.

Auth

Keyless. No registration step.

Data sources

• — study collection.
• — genome catalogues.
• — biome vocabulary.

Things that cost time to rediscover (measured 2026-09-17)

study list, but GET /v1/studies/MGYS00010519 returns Not found for a study v2 serves in full. A v1-based pack would answer "that study does not exist" about studies that do.

• This pack targets v2 deliberately. v1 is still up and still serves a

taxonlineage=, biomename= and lineage= all return the FULL unfiltered collection — same count, same first row, no error. Only search= narrows anything (studies 5,684 → 532 for "gut"; genomes 56,782 → 787 for "Prevotella"). This pack passes search through and applies the rest client-side, reporting rowsscanned and scanexhausted so a caller can tell "no matches" from "we stopped looking".

• Most query filters are silently ignored. catalogue_id=,

back whole whatever you ask, so mgnify_biomes pages it and filters here.

• search= does not work on /biomes either. The 492-row vocabulary comes

Detail URLs must NOT have one (/v2/studies/MGYS00010519).

• Collection URLs need a trailing slash (/v2/studies/?…; without it, 301).

with no indication the request was reduced.

• pagesize caps at 100 and clamps silently** — asking for 500 returns 100

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/mgnify/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"
    }
  }
}

Shortened. The full README is on GitHub.