fluxforge
by ali-kishk
README.md
# FluxForge_MCP
**The installable MCP server for [FluxForge](https://github.com/ali-kishk/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
**1. Install the package** (pulls all Python dependencies — cobra, pandas, networkx, httpx, pydantic,
mcp — and ships the ~1.5 MB runtime data bundled inside the wheel):
```bash
pip install fluxforge-mcp
```
Solver is **GLPK** (bundled with `cobra`; no CPLEX/MATLAB needed).
**2a. Claude Code — plugin marketplace** (simplest; runs `python -m mcp_server.server`, no PYTHONPATH
or data-dir env vars needed once the package is installed):
```
/plugin marketplace add ali-kishk/FluxForge_MCP
/plugin install fluxforge@fluxforge
```
**2b. Claude Code — direct:**
```bash
claude mcp add fluxforge -- python -m mcp_server.server
```
**2c. Claude Desktop — config** (`claude_desktop_config.json` → `mcpServers`):
```json
{
"mcpServers": {
"fluxforge": {
"command": "python",
"args": ["-m", "mcp_server.server"]
}
}
}
```
Use the full path to your interpreter (e.g. `.../python.exe`) if `python` isn't on the client's PATH,
or if you installed `fluxforge-mcp` into a specific virtualenv.
Only `literature.extract_claim` needs an LLM backend (configure `MCP_LLM_*`); the other 17 tools run
with no LLM.
## Verify
Ask the client to *"list your fluxforge tools"* → you should get **18**, starting with
`session.init_artifacts`. Or offline:
```bash
python -m mcp_server.server --selftest # -> registered tools: 18
```
## Data & output locations
The runtime data (Recon3D model, PPI table, regulatory map, CRISPR benchmark, comparators) ships
inside the installed package and is found automatically — no configuration needed. Outputs (session
dumps, viewers, negative-result reports) are written to `~/.fluxforge/outputs` by default. Override
either with `MCP_INPUT_DIR` / `MCP_OUTPUT_DIR` if you need a different location.
## 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.
TDQS
B3.2/5.0
Scored across 18 tools
Disambiguation5/5
Tools are clearly grouped by domain (boolean, literature, metabolic, etc.) with distinct purposes. Each tool has a unique role and no overlapping functionality is evident.
Naming Consistency5/5
All tools follow a consistent domain.tool_name snake_case naming convention, with verb_noun or verb_verb patterns that are predictable and readable.
Tool Count5/5
18 tools is appropriate for the complex multi-domain pipeline covering Boolean networks, literature, metabolic modeling, PPI, and visualization. Each tool earns its place.
Completeness5/5
The tool set covers the full pipeline from session initialization through literature extraction, constraint compilation, modeling, integration, and visualization, with crucial operations like identifier mapping and convergence checks.