MCP Directory

gget-mcp

Bioinformatics MCP server wrapping the gget toolkit for gene, sequence, structure, and enrichment queries.

Unverified
stdio (local)
No auth
Stale
Python
View repo 29

Add to your client

Copy the config for your MCP client and paste it into its config file.

Install / run
uvx --from gget-mcp@latest stdio

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "gget-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "gget-mcp@latest",
        "stdio"
      ]
    }
  }
}

Requires `uv` (the Python package runner). Install it from https://docs.astral.sh/uv/ if `uvx` is not found.

Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf

Before you start

  • uv / uvx (or Python 3.10+) to run the server
  • Stable internet connection (gget tools query external genomic databases and web services)
  • An MCP-compatible client such as Claude Desktop, Cursor, or Windsurf

About gget-mcp

gget-mcp exposes the gget bioinformatics toolkit over the Model Context Protocol, letting AI assistants run complex genomics workflows — gene search and info, sequence retrieval, BLAST/BLAT, multiple-sequence alignment, gene expression and enrichment analysis, PDB and AlphaFold protein structures, COSMIC cancer-mutation lookup, and CellxGene single-cell queries — through structured, natural-language interactions. It is built on FastMCP and distributed on PyPI as gget-mcp, runnable via uvx in STDIO, HTTP, or SSE modes.

Tools & capabilities (13)

gget_search

Find Ensembl IDs associated with search terms.

gget_info

Fetch detailed information for Ensembl IDs.

gget_seq

Retrieve nucleotide or amino acid sequences (supports translate=True for protein).

gget_ref

Get reference genome information from Ensembl.

gget_blast

BLAST nucleotide or amino acid sequences to identify their origin.

gget_blat

Find the genomic locations of sequences.

gget_muscle

Align multiple sequences (MUSCLE) and identify conserved regions.

gget_archs4

Get gene expression data from ARCHS4 across tissues.

gget_enrichr

Perform gene set enrichment / pathway analysis (Enrichr).

gget_pdb

Fetch protein structure data from the PDB.

gget_alphafold

Predict protein 3D structure using AlphaFold.

gget_cosmic

Search the COSMIC database for cancer mutations.

gget_cellxgene

Query single-cell RNA-seq data from CellxGene.

When to use it

  • Analyze a gene end-to-end: search it, fetch its details and protein sequence, then look up cancer mutations (e.g. TP53).
  • Identify the origin of an unknown DNA or protein sequence with BLAST and predict its 3D structure with AlphaFold.
  • Run pathway/enrichment analysis over a gene set (e.g. DNA-repair genes TP53, BRCA1, BRCA2, ATM).
  • Fetch gene or protein sequences and save them directly to disk (e.g. FASTA) via STDIO mode plus a filesystem extension.
  • Explore gene expression across tissues, retrieve reference genome info, or align multiple sequences to find conserved regions.

Security notes

No API key is required for the core server, but many gget tools query external web services and databases that may be rate-limited or temporarily unavailable. The optional LLM-based 'judge' tests require API keys (e.g. GEMINI_API_KEY) and may incur costs, but these are for development only and are not needed to run the server.

gget-mcp FAQ

Do I need an API key?

No. The core server requires no API key. Many tools query external public databases, so an internet connection is needed. Only the optional development 'judge' tests require LLM API keys.

Which transport modes are supported?

STDIO (recommended for MCP clients and for saving large outputs to disk), HTTP (default port 3002, endpoint /mcp, docs at /docs), and SSE.

Is this an official gget tool?

No. gget-mcp is built by the Longevity Genie project and wraps the gget library from pachterlab; it is a community/third-party MCP wrapper.

How do I run it without cloning the repo?

Use uvx, e.g. 'uvx gget-mcp http' to start the HTTP server, or 'uvx gget-mcp stdio' for STDIO mode. The MCP config uses 'uvx' with args ['--from', 'gget-mcp@latest', 'stdio'].

#bioinformatics#genomics#gget#blast#alphafold#cosmic#enrichr#ensembl#fastmcp#python

Alternatives to gget-mcp

Compare all alternatives →
Memory (Knowledge Graph)
AI, Data & Knowledge
74k

Official MCP server providing persistent, file-backed knowledge-graph memory across sessions.

Verified
stdio (local)
No auth
TypeScript
9 tools
Updated 5 months agoRepo
Sequential Thinking
AI, Data & Knowledge
62k

Structured step-by-step reasoning tool for breaking problems into revisable thought sequences.

Verified
stdio (local)
No auth
TypeScript
1 tool
Updated 6 months agoRepo
AWS Knowledge MCP
AI, Data & Knowledge
7.0k

Fully managed remote server for AWS docs, blogs, What's-New and Well-Architected guidance — no key.

Verified
HTTP (remote)
No auth
Hosted
6 tools
Updated 5 months agoRepo

Compare gget-mcp with:

vs Memory (Knowledge Graph)vs Sequential Thinkingvs AWS Knowledge MCPvs MCP Server Chart