kegg-mcp-server-python

An unofficial Python Model Context Protocol (MCP) server for the KEGG bioinformatics database. It exposes 33 tools, 8 resource templates, and 3 guided prompts to any MCP-compatible client (Claude Desktop, Claude Code, Cursor, etc.).

Built with FastMCP, returns structured Pydantic JSON (not raw text), and includes per-operation TTL caching, request retry with exponential backoff, KEGG-friendly concurrency limits, structured JSON stderr logging, and batch helpers out of the box. No API key required -- uses the free KEGG REST API.

Responses are token-aware by default: get_*_info tools return a compact EntrySummary (entry id, name, class, description, counts of linked entities) unless you pass detail_level="full". Errors are returned as a typed ErrorResult the model can reason about, not raised as exceptions.

Note: This is a community non-official project and is not affiliated with or endorsed by KEGG or Kanehisa Laboratories.

Quick start

With uvx (no install)

uvx kegg-mcp-server

With pip

pip install kegg-mcp-server
kegg-mcp-server

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "kegg": {
      "command": "uvx",
      "args": ["kegg-mcp-server"]
    }
  }
}

Claude Code

claude mcp add kegg-mcp-server -- uvx kegg-mcp-server

MCPB bundle (Claude Desktop, no Python required)

Download the latest .mcpb from the releases page and drag it onto Claude Desktop. The bundle vendors all Python dependencies and runs with Claude Desktop's embedded Python.

What's included

33 Tools

8 Resource Templates

Direct URI-based access to KEGG entities:

kegg://pathway/{pathway_id}      e.g. kegg://pathway/hsa00010
kegg://gene/{gene_id}            e.g. kegg://gene/hsa:1956
kegg://compound/{compound_id}    e.g. kegg://compound/C00002
kegg://reaction/{reaction_id}    e.g. kegg://reaction/R00756
kegg://disease/{disease_id}      e.g. kegg://disease/H00004
kegg://drug/{drug_id}            e.g. kegg://drug/D00001
kegg://organism/{org_code}       e.g. kegg://organism/hsa
kegg://search/{database}/{query} e.g. kegg://search/compound/glucose

3 Guided Prompts

Transport options

# stdio (default -- for Claude Desktop, Claude Code, uvx)
kegg-mcp-server

# Streamable HTTP (for web/API deployment)
kegg-mcp-server --transport streamable-http --host 0.0.0.0 --port 8080

# python -m also works
python -m kegg_mcp_server

Development

git clone https://github.com/Lucas-Servi/kegg-mcp-server-python
cd kegg-mcp-server-python
pip install -e ".[dev]"

# Run tests
pytest tests/ -v

# Lint
ruff check src/ tests/

# Debug with MCP Inspector
mcp dev kegg-mcp-server

Project structure

src/kegg_mcp_server/
  server.py       FastMCP instance, lifespan (httpx client + TTL cache), CLI
  client.py       KEGGClient: async KEGG REST with retry/backoff + KEGG-politeness semaphore
  cache.py        Per-op TTL cache (info 24h, list 1h, entry ops 5min)
  parsers.py      KEGG flat-file and tab-delimited response parsers + summarize_flat_entry
  errors.py       KEGGAPIError exception type
  logging.py      JSON stderr logger (stdout is reserved for MCP stdio framing)
  resources.py    8 MCP resource templates
  prompts.py      3 bioinformatics workflow prompts
  models/         Pydantic models for all KEGG entity types + EntrySummary + ErrorResult
  tools/          13 tool modules, each with a register(mcp) function; _common.py has the
                  @kegg_tool error-boundary decorator and shared READ_ONLY annotations

Author

Developed by Lucas Servi (lucasservi@gmail.com) at Elytron Biotech using Claude Code.

Acknowledgments

• Based on Augmented-Nature/KEGG-MCP-Server -- the original TypeScript implementation that served as the foundation for this Python rewrite
• KEGG -- Kyoto Encyclopedia of Genes and Genomes (Kanehisa Laboratories)
• Model Context Protocol -- Anthropic's open protocol for LLM tool use

License

MIT -- see LICENSE.