gcMeta-MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
gcMeta-MCP
An MCP (Model Context Protocol) server that provides LLMs with access to the gcMeta (Global Catalogue of Metagenomics) platform.
English | 中文
📋 Table of Contents
Related MCP server: geo-mcp
Overview
gcMeta-MCP is a Model Context Protocol (MCP) server that bridges Large Language Models (LLMs) with the gcMeta — the Global Catalogue of Metagenomics platform maintained by WDCM / NMDC.
By exposing gcMeta's rich metagenomics data as MCP tools, this server enables LLM-powered assistants to search, retrieve, and analyze metagenomics data — including BioProjects, BioSamples, sequencing Runs, Metagenome-Assembled Genomes (MAGs), Biome Catalogues, Taxonomy Abundance, and Functional Annotations — all through natural language queries.
Background
gcMeta is a global repository of metagenome-assembled genomes (MAGs) enabling cross-ecosystem microbial discovery and function research. As of 2026, it hosts:
Metric | Count |
Total MAGs | 3,917,189 |
All MAGs under catalogues | 2,756,886 |
Species-level representative MAGs | 109,586 |
Runs | 177,196 |
BioSamples | 127,760 |
BioProjects | 9,653 |
The platform organizes MAGs into 50+ Biome Catalogues spanning diverse ecosystems:
Human: Gut, Skin, Vaginal
Animals: Chicken, Pig, Cattle, Mouse, Cat, Dog, Horse, Goat, Sheep, etc.
Marine: Seawater, Sediment
Freshwater: Lake Water, Riverine, Sediment
Environments: Agricultural Soil, Hot Spring, Permafrost, Wastewater, etc.
Extreme Environments: Acid, Cold, Hot, Pressure, Saline-alkaline Habitats
Plant Rhizosphere: Rice, Wheat, Arabidopsis, Bean
Wild Animals: Bear, Deer, Elephant, Giant Panda, Koala, Vulture, etc.
gcMeta also provides functional annotation across several categories: Antibiotics Resistance Genes (ARGs), KEGG Pathways, Virulence Factors (VFs), Carbohydrate-Active enZYmes (CAZy), Biosynthetic Gene Clusters (BGCs), Mobile Genetic Elements (MGEs), and Defense Systems.
Features
🔌 MCP Protocol Support — Full compatibility with the Model Context Protocol specification.
🧬 13 Tools — Search and retrieve BioProjects, BioSamples, Runs, MAGs, Biome Catalogues, Taxonomy Abundance, Functional Annotations, and platform statistics.
🌐 Type-safe — Written in TypeScript with Zod schema validation for all inputs.
⚡ Lightweight — Minimal dependencies, stdio-based transport, no external server required.
🔧 Configurable — Custom base URL, authentication token, and timeout settings.
📦 Zero-config — Works out of the box with
npxor direct installation.
Prerequisites
Node.js >= 18.0.0
An MCP-compatible client (e.g., Claude Desktop, Cursor, or any MCP client)
Installation
Option 1: Using npx (recommended — no installation needed)
npx gcmeta-mcpOption 2: Global installation
npm install -g gcmeta-mcp
gcmeta-mcpOption 3: Local development
git clone https://github.com/zengzichao/gcMeta-MCP.git
cd gcMeta-MCP
npm install
npm run build
npm startConfiguration
The server reads configuration from environment variables:
Variable | Description | Default |
| Base URL of the gcMeta instance |
|
| Optional authentication token | (none) |
Copy .env.example to .env and adjust as needed:
cp .env.example .envUsage
Claude Desktop
Add the following to your Claude Desktop configuration file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"gcmeta": {
"command": "npx",
"args": ["-y", "gcmeta-mcp"]
}
}
}For local development:
{
"mcpServers": {
"gcmeta": {
"command": "node",
"args": ["/path/to/gcMeta-MCP/dist/index.js"]
}
}
}Other MCP Clients
This server uses stdio transport, making it compatible with any MCP-compliant client. Simply configure your client to run npx -y gcmeta-mcp as the server command.
Direct Execution
# After installation or building from source
node dist/index.js
# With custom base URL
GCMETA_BASE_URL=https://gcmeta.wdcm.org node dist/index.jsAvailable Tools
The server exposes 13 tools:
# | Tool | Description |
1 |
| Search for BioProjects by keyword, organism, etc. |
2 |
| Get detailed info about a single BioProject |
3 |
| Search for BioSamples with multiple filters |
4 |
| Get detailed info about a single BioSample |
5 |
| Search for sequencing Runs |
6 |
| Get detailed info about a single Run |
7 |
| Search for Metagenome-Assembled Genomes (MAGs) |
8 |
| Get detailed info about a single MAG |
9 |
| List all available biome catalogues |
10 |
| Get detailed info about a specific biome catalogue |
11 |
| Get taxonomy abundance for a sample or catalogue |
12 |
| Search functional annotations (ARGs, KEGG, CAZy, etc.) |
13 |
| Get aggregate platform statistics |
See the API Reference for detailed input/output specifications of each tool.
Development
# Install dependencies
npm install
# Build
npm run build
# Watch mode
npm run dev
# Lint
npm run lint
# Format
npm run formatProject Structure
gcMeta-MCP/
├── src/
│ ├── index.ts # Server entry point
│ ├── gcmeta-client.ts # gcMeta HTTP API client
│ ├── tools.ts # MCP tool definitions
│ └── types.ts # TypeScript type definitions
├── docs/
│ ├── en/ # English documentation
│ │ ├── INSTALLATION.md
│ │ ├── API.md
│ │ └── CONFIGURATION.md
│ └── zh/ # Chinese documentation
│ ├── 安装指南.md
│ ├── API文档.md
│ └── 配置说明.md
├── examples/
│ └── claude-desktop-config.json
├── package.json
├── tsconfig.json
├── eslint.config.js
├── .prettierrc
├── .editorconfig
├── .env.example
├── .gitignore
├── LICENSE
├── README.md # English (this file)
├── README_zh.md # Chinese
├── CHANGELOG.md
├── CONTRIBUTING.md
└── CONTRIBUTING_zh.mdDocumentation
Contributing
Contributions are welcome! Please read the Contributing Guide (中文: 贡献指南) for details on how to submit pull requests, report issues, and suggest features.
License
This project is licensed under the MIT License.
Citation
If you use gcMeta-MCP in your research, please cite both the tool and the gcMeta platform:
@software{gcmeta-mcp,
title = {gcMeta-MCP: An MCP Server for the Global Catalogue of Metagenomics},
author = {Zeng, Zichao},
year = {2026},
version = {0.1.0},
url = {https://github.com/zengzichao/gcMeta-MCP}
}Acknowledgements
gcMeta — Global Catalogue of Metagenomics, maintained by WDCM / NMDC
Model Context Protocol — The protocol specification
WDCM — World Data Centre for Microorganisms
NMDC — National Microbiology Data Center
This server cannot be deployed
Maintenance
Related MCP Connectors
MGnify — EMBL-EBI's metagenomics resource: public microbiome studies, the biome vocabulary they…
Entity-resolved NIH grant corpus (FY1985-2026) via 14 read-only, provenance-carrying MCP tools.
Find, vet, and run MCP tools through a secure audited gateway with prompt-injection risk scoring
Related MCP Servers
- AlicenseBqualityDmaintenanceThis MCP server provides 16 intelligent tools for searching, retrieving, and linking biomedical literature from PubMed and PMC. It enables LLM applications to perform complex queries, batch processing, and cross-database linking.168MIT
- AlicenseBqualityDmaintenanceEnables searching and downloading Gene Expression Omnibus (GEO) data from NCBI, including datasets, series, samples, platforms, and profiles, through natural language queries.11118 PyPI18BSD 3-Clause
- FlicenseAqualityCmaintenanceAn MCP server that gives Claude access to NCBI Datasets v2 — search genome assembly metadata, retrieve taxonomy records, and download data packages without leaving your conversation.10-
- AlicenseNot gradedqualityBmaintenanceMCP server for querying the GWAS Catalog (EBI/NHGRI), a curated catalog of genome-wide association studies. It enables AI agents to search and retrieve study data via natural language or direct tool calls.485 npmMIT