amr-mcp

An MCP server that lets AI assistants (Claude, Codex, Cursor…) query antimicrobial resistance (AMR) data from public, free sources:

• NCBI Reference Gene Catalog, the curated database behind AMRFinderPlus: ~11,500 AMR genes, point mutations, stress and virulence genes
• NCBI E-utilities: protein and nucleotide sequences, PubMed references
• UniProtKB: protein function, keywords and cross-references
• AMRFinderPlus (optional, if installed locally): screen your own genomes

All data sources are public domain or freely accessible; no API keys are required.

Demo

Claude Code answering the first example question below: the server looks up blaKPC-2 in the catalog, counts the species NCBI has found it in, pulls the protein sequence and resolves the original paper.

Example questions

Which species carry the KPC-2 carbapenemase, what is the original paper describing it, and what does its protein sequence look like?

Summarise the carbapenemase gene families in the catalog and how many variants each has.

Give me the protein sequence of mcr-1.1 and its UniProt function annotation.

Run AMRFinderPlus on ~/data/isolate_17.fasta as Escherichia and explain the hits by drug class.

Tools

Installation

Run it with uv (no install step needed), or pip install amr-mcp.

Claude Code

claude mcp add amr -- uvx amr-mcp

Claude Desktop

Add to claude_desktop_config.json:

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

Without uv: pipx

pipx install amr-mcp
which amr-mcp   # e.g. /Users/you/.local/bin/amr-mcp

Then use that absolute path as the command, for example in claude_desktop_config.json:

{
  "mcpServers": {
    "amr": { "command": "/Users/you/.local/bin/amr-mcp" }
  }
}

Desktop apps don't inherit your shell's PATH, so if Claude Desktop can't start the server, use the absolute path for the command (this applies to uvx too: run which uvx to get it).

Agent skill (optional)

skills/amr-research/SKILL.md tells the agent when to reach for these tools and how to chain them (gene → hosts → sequence → paper, family overviews, genome screening), plus the pitfalls to avoid. It works with any agent that reads SKILL.md files (Claude Code, Cursor, Codex, Copilot…):

npx skills add pabloestepaa/amr-mcp

Or copy the folder by hand, e.g. to ~/.claude/skills/amr-research/ for Claude Code. The skill uses the MCP server above, so install that too.

Configuration

To enable run_amrfinder: conda install -c bioconda ncbi-amrfinderplus && amrfinder -u.

Development

python -m venv .venv && .venv/bin/pip install -e ".[dev]"
.venv/bin/pytest -m "not network"   # offline tests
.venv/bin/pytest                    # also hits the live NCBI/UniProt APIs

Data licensing

The NCBI Reference Gene Catalog and NCBI sequence data are US government works in the public domain. UniProt data is available under CC BY 4.0. Please cite the original sources when you publish results:

• Feldgarden M, et al. AMRFinderPlus and the Reference Gene Catalog facilitate examination of the genomic links among antimicrobial resistance, stress response, and virulence. Sci Rep. 2021.
• The UniProt Consortium. UniProt: the Universal Protein Knowledgebase. Nucleic Acids Res.

License

MIT

Developed with AI assistance (Claude Code); all code reviewed and tested by the author.