Using discopt from Claude Desktop (MCP server)

Using discopt from Claude Desktop (MCP server)#

discopt mcp runs a Model Context Protocol server on stdio. Any MCP client can then build and solve discopt models on your machine: Claude Desktop, Claude Code, or another one.

Install and register#

pip install 'discopt[mcp]'
discopt mcp --print-config

The second command prints the entry to merge into Claude Desktop’s claude_desktop_config.json. On macOS that file is ~/Library/Application Support/Claude/claude_desktop_config.json; on Windows it is %APPDATA%\Claude\claude_desktop_config.json. The entry looks like this:

{
  "mcpServers": {
    "discopt": {
      "command": "/path/to/your/python",
      "args": ["-m", "discopt.cli", "mcp"]
    }
  }
}

It names the absolute path of the Python that has discopt installed. Desktop does not inherit your shell’s PATH, so a bare discopt command is often not found there. Restart Desktop after editing the file.

For Claude Code, register the same command:

claude mcp add discopt -- "$(python -c 'import sys; print(sys.executable)')" -m discopt.cli mcp

Tools#

Tool

What it does

solve_python

Runs Python source that builds a Model named model or m, then solves it

solve_file

Solves a .nl, .gms, saved model document (.dopt, .json, .json.gz) or a .py script

model_summary

Describes a model’s size and structure without solving it

convert_model

Converts between .gms, .nl, .mps and .lp

discopt_info

Reports the version, the install location and the Python running the server

A solve returns the same fields as discopt solve --format json: status, objective, bound, gap, gap_certified, wall_time, node_count and the solution x. x is truncated to max_vars entries (default 200), and when that happens x_truncated says how many entries there were. time_limit defaults to 60 s per call. A result is a proven global optimum only when status is optimal and gap_certified is true.

How it runs#

Each request runs in a fresh worker process, never in the server process. There are three reasons:

  • Clean protocol stream. The stdio transport is the server’s stdout, so anything a solver or a model script prints there would corrupt it. The worker redirects its own stdout to stderr and returns its result on a private channel.

  • Hard timeout. A worker still running 60 s past its time_limit is killed, and the call returns an error instead of hanging the client.

  • Crash isolation. A crash takes down the worker, not the server.

Errors are returned as {"ok": false, "error": ..., "stderr_tail": ...}, with the tail of the worker’s traceback.

Warning

solve_python and .py files execute arbitrary Python as the user running the server. That is how a client writes a model, and it is no more than a client with a shell tool could do. Register the server only with clients you would trust with a shell.