Gget

gget-mcp

MCP (Model Context Protocol) server for the gget bioinformatics library.

This server implements the Model Context Protocol (MCP) for gget, providing a standardized interface for accessing powerful bioinformatics tools and databases. MCP enables AI assistants and agents to perform complex genomics queries through structured interfaces.

The gget bioinformatics toolkit provides efficient querying of genomic databases and includes functions for:

• Gene and sequence information retrieval
• BLAST and sequence alignment
• Protein structure prediction
• Gene expression analysis
• Functional enrichment analysis
• And much more!

🚀 Quick Example: What Can You Do?

👤 User: "Analyze the TP53 gene - find its details and protein sequence, then check for cancer mutations"

🤖 AI Assistant: I'll help you analyze TP53 step by step:

[Uses gget_search] → Found TP53 (ENSG00000141510) on chromosome 17
[Uses gget_info] → TP53 is a protein-coding tumor suppressor gene
[Uses gget_seq with translate=True] → Retrieved 393 amino acid protein sequence
[Uses gget_cosmic] → Found hotspot mutations R175H, R248Q, R273H in multiple cancers

👤 User: "Now predict the 3D structure of this protein sequence: MSKGEELFTGVVPILVEL..."

🤖 AI Assistant: Let me analyze this sequence:

[Uses gget_blast] → Identified as Green Fluorescent Protein (GFP)
[Uses gget_alphafold] → Predicted classic beta-barrel structure with 90%+ confidence

👤 User: "Perform pathway enrichment for DNA repair genes: TP53, BRCA1, BRCA2, ATM"

🤖 AI Assistant: [Uses gget_enrichr] → Top pathways: DNA Damage Response, Homologous Recombination, Cell Cycle Checkpoints, p53 Signaling

See how powerful this is? You can now ask natural language questions about genes, sequences, mutations, and pathways - the AI does the complex bioinformatics work for you!

About MCP (Model Context Protocol)

MCP is a protocol that bridges the gap between AI systems and specialized domain tools. It enables:

• Structured Access: Direct connection to powerful bioinformatics tools and databases
• Natural Language Queries: Simplified interaction with complex genomics workflows
• Type Safety: Strong typing and validation through FastMCP
• AI Integration: Seamless integration with AI assistants and agents

If you want to understand more about what the Model Context Protocol is and how to use it more efficiently, you can take the DeepLearning AI Course or search for MCP videos on YouTube.

Available Tools

Gene Information & Search

• 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
• gget_ref: Get reference genome information from Ensembl

Sequence Analysis

• gget_blast: BLAST nucleotide or amino acid sequences
• gget_blat: Find genomic locations of sequences
• gget_muscle: Align multiple sequences

Expression & Functional Analysis

• gget_archs4: Get gene expression data from ARCHS4
• gget_enrichr: Perform gene set enrichment analysis

Protein Structure & Function

• gget_pdb: Fetch protein structure data from PDB
• gget_alphafold: Predict protein structure using AlphaFold

Cancer & Mutation Analysis

• gget_cosmic: Search COSMIC database for cancer mutations

Single-cell Analysis

• gget_cellxgene: Query single-cell RNA-seq data from CellxGene

Quick Start

# Download and install uv
curl -LsSf https://astral.sh/uv/install.sh | sh

# Verify installation
uv --version
uvx --version

uvx is a very nice tool that can run a python package installing it if needed.

Running with uvx

You can run the gget-mcp server directly using uvx without cloning the repository:

# Run the server in HTTP mode (default)
uvx gget-mcp http

STDIO Mode (for MCP clients that require stdio)

# Run the server in stdio mode
uvx gget-mcp stdio

HTTP Mode (Web Server)

# Run the server in streamable HTTP mode on default (3002) port
uvx gget-mcp http

# Run on a specific port
uvx gget-mcp http --port 8000

SSE Mode (Server-Sent Events)

# Run the server in SSE mode
uvx gget-mcp sse

In cases when there are problems with uvx often they can be caused by cleaning uv cache:

uv cache clean

The HTTP mode will start a web server that you can access at http://localhost:3002/mcp (with documentation at http://localhost:3002/docs). The STDIO mode is designed for MCP clients that communicate via standard input/output, while SSE mode uses Server-Sent Events for real-time communication.

Note: Currently, we do not have a Swagger/OpenAPI interface, so accessing the server directly in your browser will not show much useful information. To explore the available tools and capabilities, you should either use the MCP Inspector (see below) or connect through an MCP client to see the available tools.

Configuring your AI Client (Anthropic Claude Desktop, Cursor, Windsurf, etc.)

We provide preconfigured JSON files for different use cases. Here are the actual configuration examples:

STDIO Mode Configuration (Recommended)

Use this configuration for most AI clients. Use this mode when you want to save large output files (sequences, structures, alignments) to disk instead of returning them as text. Create or update your MCP configuration file:

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

HTTP Mode Configuration

For HTTP mode:

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

Configuration Video Tutorial

For a visual guide on how to configure MCP servers with AI clients, check out our configuration tutorial video for our sister MCP server (biothings-mcp). The configuration principles are exactly the same for the gget MCP server - just use the appropriate JSON configuration files provided above.

Inspecting gget MCP server

If you want to inspect the methods provided by the MCP server, use npx (you may need to install nodejs and npm):

For STDIO mode with uvx:

npx @modelcontextprotocol/inspector --config mcp-config.json --server gget-mcp

You can also run the inspector manually and configure it through the interface:

npx @modelcontextprotocol/inspector

After that you can explore the tools and resources with MCP Inspector at which is usually at 6274 port (note, if you run inspector several times it can change port)

Integration with AI Systems

Simply point your AI client (like Cursor, Windsurf, ClaudeDesktop, VS Code with Copilot, or others) to use the appropriate configuration file from the repository.

Platform-Specific Setup Guides

Claude Desktop + gget_mcp Step-by-Step Guide (Windows)

Overview

This guide will walk you through setting up Claude Desktop with the gget_mcp extension and Google Drive integration on Windows. By the end, you'll be able to use Claude to fetch biological data (like gene sequences) and save them directly to your Google Drive folder with offline access.

Prerequisites

• Windows PC with administrator access
• Google account
• Stable internet connection

Step 1: Set Up Google Drive for Desktop with Offline Access

1. Download and install Google Drive for Desktop

2. Launch the application and sign in with your user account

3. Connect your project's shared Google account (if applicable)

4. Configure offline access for your working folder:

   • Navigate to the folder you want to work with in Google Drive
   • Right-click on the folder (e.g., "work" or your project folder)
   • Select "Available offline" from the context menu
   • This makes the folder accessible at a path like C:\GDrive\holy-bio-mcp\My Disk\work

   Important: This is different from just syncing - offline access ensures the files are locally available while still being part of your Google Drive structure.

Step 2: Install Claude Desktop

1. Download Claude Desktop for Windows
2. Run the installer and follow the setup wizard
3. Sign in with your Anthropic/Claude account
4. Complete the initial setup

Step 3: Install uv Package Manager

1. Install uv using one of these methods:

   Option A: Using winstall

   • Visit https://winstall.app/apps/astral-sh.uv
   • Follow installation instructions

   Option B: Using PowerShell

   powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

   Copy to clipboard

2. Restart your terminal after installation

Step 4: Install Node.js

You can install Node.js using either method:

Option A: Native Installer

1. Visit https://nodejs.org/en/download
2. Download the Windows installer (LTS version recommended)
3. Run the installer with default settings

Option B: Using Chocolatey

choco install nodejs

Both methods work equally well - choose whichever you prefer.

Step 5: Verify Installation & Cache Packages

Open Command Prompt or PowerShell and run:

uvx --from gget-mcp@latest stdio

Expected behavior:

• The command should start without errors
• Packages will be downloaded and cached
• If it runs successfully, everything is configured correctly
• You can press Ctrl+C to stop it

Step 6: Configure Claude Desktop

6.1: Enable Filesystem Extension

1. Open Claude Desktop
2. Go to Settings (gear icon)
3. Navigate to the "Extensions" tab in the left sidebar
4. Enable the Filesystem Extension
5. Add your Google Drive offline folder to the allowed directories (e.g., C:\GDrive\holy-bio-mcp\My Disk\work)

Note: The Filesystem extension is built into Claude Desktop and uses MCP under the hood, but it's managed directly by the application. You don't need to configure it in the JSON file.

6.2: Add gget_mcp Server

1. In the same manner, go to Settings, navigate to the "Developer" tab in the left sidebar
2. In Developer settings tab, click "Edit Config" button
3. This will open the claude_desktop_config.json file
4. Edit it and add the gget_mcp server configuration:

{
  "mcpServer

…