Log inSubmit server
Mygene Info logo

Mygene Info

Queries MyGene.info for gene annotations, batch lookups, metadata, and taxonomy through MCP.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Mygene Info

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "mygene-info": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-mygene-info"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y @pipeworx/mcp-mygene-info

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 4d ago.

Overview

Mygene Info MCP server connects AI clients to the MyGene.info v3 gene annotation service. It provides tools for gene search, single-gene annotation retrieval, batch identifier lookup, release metadata, and species taxonomy. Use it when an agent needs joined gene data from sources such as NCBI, Ensembl, UniProt, KEGG, or OMIM without managing an API key. It can run locally over stdio or remotely through the Pipeworx gateway.

Use cases

  • Search for genes by name or text
  • Retrieve annotations for Entrez or Ensembl identifiers
  • Batch-resolve multiple gene identifiers
  • Inspect MyGene.info release and source metadata
  • Look up taxonomy information for a species

Key features

  • Full-text gene queries
  • Single-gene annotation retrieval
  • Batch identifier lookups
  • Release and source metadata
  • Species taxonomy queries
  • Local stdio and remote gateway access

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

7/7 checks healthy over the last 47d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 15d ago via OSV.dev · @pipeworx/mcp-mygene-info (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads495Package downloads in the last 30 days.
Last commit28d agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Mygene Info works

What the Mygene Info MCP server does

The Mygene Info MCP server exposes gene annotation operations from MyGene.info through the Model Context Protocol. MyGene.info joins annotation data from sources including NCBI, Ensembl, UniProt, KEGG, and OMIM on a per-gene basis. The service is keyless, so the package does not require a MyGene.info API key for its documented setup.

Use it to search genes by text, retrieve annotations for a known identifier, resolve multiple identifiers in one request, inspect service metadata, or look up taxonomy information for a species. Gene identifiers can be Entrez or Ensembl IDs, depending on the operation and supplied arguments.

Tools and capabilities

The Mygene Info MCP server defines five primary tools:

  • query(query, species?, fields?, size?, sort?) performs a full-text gene search. Optional parameters can narrow the species, select returned fields, limit result count, or control sorting.
  • gene(gene_id, fields?, species?) retrieves annotations for one gene identifier.
  • query_many(ids, scopes?, species?, fields?) performs a batch lookup for multiple identifiers, with optional identifier scopes, species, and field selection.
  • metadata() returns release and source metadata.
  • taxonomy(species) returns taxonomy information for a species.

The underlying data source is https://mygene.info/v3/.

Setup and configuration

For a local installation, add the package as an MCP server using npx -y @pipeworx/mcp-mygene-info, or run that command directly to verify that it starts. The local process communicates over stdin and stdout and exposes only the five pack tools. It does not need a Pipeworx account or a gateway round trip.

A remote MCP connection is also available at https://gateway.pipeworx.io/mygene-info/mcp. This endpoint lists the pack tools along with shared Pipeworx meta-tools. Its initialize response is the authoritative source for the exact tools exposed at a given time. The full gateway endpoint, https://gateway.pipeworx.io/mcp, lists all available packs directly; both gateway URLs can use ask_pipeworx to route questions across the catalog.

The tools can also be called over HTTP. For example, a POST request to https://gateway.pipeworx.io/v1/tools/mygene_info_query can submit a JSON body containing a gene query such as {"query":"BRCA1"}. The documented gateway examples state that no account is needed for the first calls.

Limitations and notes

The local and gateway connections expose different tool lists. Local stdio provides only the Mygene Info pack, while the gateway pack endpoint adds shared Pipeworx tools such as discovery, search, memory, and cross-catalog question routing. Those shared tools are not additional MyGene.info operations.

Field availability and annotation contents are determined by MyGene.info and its joined source data.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Mygene Info

Mygene Info is an MCP server that connects AI clients to the MyGene.info v3 gene annotation service. Its main tools query genes, retrieve annotations by Entrez or Ensembl ID, perform batch lookups, inspect release metadata, and return species taxonomy information. It requires no API key.

Install it by configuring an MCP client to run `npx -y @pipeworx/mcp-mygene-info`. This starts the standalone local stdio server without a Pipeworx account. You can also connect to the hosted MCP endpoint at `https://gateway.pipeworx.io/mygene-info/mcp`.

Yes, Mygene Info works with Cursor. Add the hosted MCP URL to Cursor's MCP configuration, or configure the local `npx -y @pipeworx/mcp-mygene-info` command as a stdio server.

Use the `query` tool with a text value such as `BRCA1`. The tool supports optional species, fields, size, and sort parameters. For a known Entrez or Ensembl identifier, use `gene`; for multiple identifiers, use `query_many`.

Yes, call the gateway tool endpoint with a JSON POST request. For example, send `{"query":"BRCA1"}` to `https://gateway.pipeworx.io/v1/tools/mygene_info_query` with a JSON content type header.

Related MCP servers

All in Biology & Bioinformatics All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewMygene Info AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/mygene-info?style=directory)](https://allmcps.com/mcp/mygene-info)
HTML Embed
<a href="https://allmcps.com/mcp/mygene-info"><img src="https://allmcps.com/api/badge/mygene-info?style=directory" alt="Mygene Info on AllMCPs" /></a>