FluxForge_MCP

The installable MCP server for FluxForge — a fail-closed Model Context Protocol server that fuses literature, regulatory/PPI networks, and genome-scale metabolic models to predict CRISPR gene dependencies and drug targets. 18 typed tools.

This is a lightweight distribution repo (server + ~1.5 MB runtime data only) so it clones and installs fast. The full research code — the benchmark engine, datasets, figures, and paper materials — lives in the main repo: https://github.com/ali-kishk/FluxForge.

Install

Claude Code — plugin marketplace:

/plugin marketplace add ali-kishk/FluxForge_MCP
/plugin install fluxforge@fluxforge

Claude Code — direct (pins the interpreter that has the deps):

claude mcp add fluxforge -- python -m mcp_server.server
# add -e PYTHONPATH=/abs/path/to/FluxForge_MCP if `python` can't import mcp_server

Claude Desktop — config (claude_desktop_config.json → mcpServers):

{
  "mcpServers": {
    "fluxforge": {
      "command": "python",
      "args": ["-m", "mcp_server.server"],
      "env": { "PYTHONPATH": "/abs/path/to/FluxForge_MCP" }
    }
  }
}

Use the full path to your interpreter (e.g. .../python.exe) if python isn't on the client's PATH.

Related MCP server: GenomeMCP

Prerequisite (important)

The plugin ships the server + runtime data, not the Python scientific dependencies (they contain compiled, platform-specific code that can't be portably bundled). The python the client launches must have them:

pip install mcp cobra pandas networkx httpx pydantic

Only literature.extract_claim needs an LLM backend (configure MCP_LLM_*); the other 17 tools run with no LLM. Solver is GLPK (no CPLEX/MATLAB needed).

Verify

Ask the client to "list your fluxforge tools" → you should get 18, starting with session.init_artifacts. Or offline:

python -m mcp_server.server --selftest    # -> registered tools: 18

License & citation

Apache-2.0 (see LICENSE / NOTICE) — © 2026 Ali Kishk. Cite via CITATION.cff. For the benchmark methodology and results, cite the main FluxForge repo / preprint.