EVEE MCP Server

MCP server for the EVEE (Evo Variant Effect Explorer) API — interpretable variant effect prediction from Evo 2 genomic foundation model embeddings.

EVEE provides pre-computed pathogenicity predictions, disruption profiles, and AI-generated mechanistic interpretations for 4.2 million ClinVar variants. See Pearce et al. (2026) for the full paper.

Tools

Annotation categories

amino_acid, atacseq, ccre, chipseq, chromhmm, elm, fstack, protein_feature, interpro, genomic_feature, ptm, region, secondary_structure

Skill

A Claude Code skill lives at .claude/skills/evee/SKILL.md. Agents that load it get ~120 lines of guidance on how to use the tools effectively — workflow steps, reliability caveats by variant class, and gotchas (0-based coords, indel VCF anchoring, case-sensitivity).

Usage

Requires Python 3.10+ and uv.

git clone git@github.com:goodfire-ai/evee-mcp.git
cd evee-mcp
uv sync

Claude Code

The repo ships a .mcp.json; opening the directory triggers the permission prompt:

claude

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "evee": {
      "command": "uv",
      "args": ["run", "--directory", "/absolute/path/to/evee-mcp", "python3", "server.py"]
    }
  }
}

Example

Is the FBN1 variant rs1597537935 pathogenic, and why?

The agent searches, fetches the clinical summary with the AI-generated mechanistic interpretation, and pulls out the top disruption evidence.