glen-mcp-opt

An MCP server that lets an LLM turn optimization questions into models and solve them. The LLM writes the model as JSON; the server validates it, classifies it (LP, ILP, MILP, ...), solves it with HiGHS, and returns results in a form the LLM can explain. Built for GLEN; works with any MCP client.

Tools

Example spec (choose projects within a budget):

{
  "sets": { "A": ["a1", "a2", "a3"] },
  "params": {
    "cost":    { "index": "A", "values": { "a1": 3, "a2": 5, "a3": 2 } },
    "benefit": { "index": "A", "values": { "a1": 4, "a2": 7, "a3": 2 } },
    "budget": 6
  },
  "variables":   { "x": { "index": "A", "type": "binary" } },
  "objective":   { "sense": "max", "expr": "sum(benefit[a] * x[a] for a in A)" },
  "constraints": { "budget": "sum(cost[a] * x[a] for a in A) <= budget" }
}

Expressions are parsed against a whitelist; no code is executed. Sets and params can come from a DuckDB query over S3 Parquet ({"source": "sql", "query": ...}), so data rows never pass through the LLM. Full reference: src/glen_opt/guide.md.

Related MCP server: MCP Optimizer

Run

python -m venv .venv && .venv/bin/pip install -e '.[dev]'
.venv/bin/glen-mcp-opt        # http://localhost:8000/mcp
.venv/bin/pytest

Try it from Claude Code:

claude mcp add --transport http glen-opt http://localhost:8000/mcp

Outside the NRP cluster, set S3_DEFAULT_ENDPOINT=s3-west.nrp-nautilus.io for SQL sources.

Use with GLEN

Add the server after duckdb-mcp in the app's layers-input.json:

"mcp_servers": [
  { "url": "https://duckdb-mcp.nrp-nautilus.io/mcp" },
  { "url": "https://glen-opt.nrp-nautilus.io/mcp", "optional": true }
]

Deploy

Pushes to main build ghcr.io/schmidtdse/glen-mcp-opt:main.

kubectl apply -f k8s/

Evaluate

eval/problems.json holds plain-language questions with known optimal values. The runner sends each to an LLM through open-llm-proxy, executes its tool calls against this server, and scores the result:

PROXY_KEY=... .venv/bin/python eval/run_eval.py --models kimi qwen3

License

BSD-3-Clause