evo2-nim-mcp

zzgael/evo2-nim-mcp

★ 0 stars Python 🤖 AI/LLM Updated 1d ago

LLM-optimized MCP server for the NVIDIA NIM Evo2 container — DNA scoring, embeddings, generation, splice + variant analysis

View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "evo2-nim-mcp": {
      "command": "uvx",
      "args": [
        "evo2-nim-mcp"
      ]
    }
  }
}

Or install with pip: pip install evo2-nim-mcp

README Excerpt

LLM-optimized MCP server for the [NVIDIA NIM Evo2 container](https://docs.nvidia.com/nim/bionemo/evo2/latest/) — exposes the Arc Institute Evo2 DNA language model (40B or 7B) as a clean set of tools any MCP-aware client (Claude Desktop, Cursor, the MCP Inspector, custom agents) can call: scoring, batch scoring, embeddings, generation, SNP and splice variant analysis, and Ensembl-backed convenience helpers.

Tools (18)

ENSEMBL_CONNECT_TIMEOUTENSEMBL_REQUEST_TIMEOUTEVO2_CONNECT_TIMEOUTEVO2_NGC_API_KEYEVO2_NIM_URLEVO2_REQUEST_TIMEOUTembed_sequenceembed_similarityfetch_variant_contextgenerate_sequencelist_available_checkpointslist_layer_namesnim_healthscore_sequencescore_snpscore_splice_regionscore_variant_atscore_variant_batch

evo2-nim-mcp

Quick Install

README Excerpt

Tools (18)

Related AI/LLM Servers