Show HN: Constraint Programming in Your AI Agent

A developer released minizinc-mcp, an MCP server that exposes MiniZinc constraint solving and optimization to LLM clients including opencode, Claude Desktop, and Cursor, letting agents parse, type-check, and solve MiniZinc models directly from a chat session. Built with the MCP Python SDK v2 and the MiniZinc Python binding, the server requires only uv and MiniZinc 2.6+ with the minizinc executable on PATH, and installs via `uv tool install --from git+https://github.com/carban/minizinc-mcp minizinc-mcp` or runs on demand with uvx. It exposes six tools prefixed with minizinc_ — minizinc_list_solvers, minizinc_validate_model, minizinc_solve_model, minizinc_solve_model_by_path, minizinc_get_model_info, and minizinc_get_flatzinc — and runs over stdio.

An MCP https://modelcontextprotocol.io server that exposes MiniZinc https://www.minizinc.org/ constraint solving and optimization to LLM clients such as opencode, Claude Desktop, and Cursor. It lets an agent parse, type-check, and solve MiniZinc models directly from a chat session. Built with the MCP Python SDK v2 https://py.sdk.modelcontextprotocol.io/ and the MiniZinc Python binding https://pypi.org/project/minizinc/ . Only two things need to be installed, once per machine : - uv https://docs.astral.sh/uv/ — curl -LsSf https://astral.sh/uv/install.sh | sh - MiniZinc https://www.minizinc.org/ 2.6+ with the minizinc executable on PATH includes a default solver, Gecode Everything else is fetched automatically by uv — there is no clone, no venv setup, and no manual pip install on your side. Install it globally best if you use it in several projects : uv tool install --from git+https://github.com/carban/minizinc-mcp minizinc-mcp Or run it on demand each time, with nothing installed: uvx --from git+https://github.com/carban/minizinc-mcp minizinc-mcp The server runs over stdio. Tell your MCP client to launch it: opencode — project level add this to opencode.jsonc in your project : { "$schema": "https://opencode.ai/config.json", "mcp": { "minizinc": { "type": "local", "command": "uvx", "--from", "git+https://github.com/carban/minizinc-mcp", "minizinc-mcp" } } } opencode — global add the same mcp.minizinc block to ~/.config/opencode/opencode.json : { "mcp": { "minizinc": { "type": "local", "command": "uvx", "--from", "git+https://github.com/carban/minizinc-mcp", "minizinc-mcp" } } } Claude Desktop claude desktop config.json : { "mcpServers": { "minizinc": { "command": "uvx", "args": "--from", "git+https://github.com/carban/minizinc-mcp", "minizinc-mcp" } } } Restart your client. Six tools should now be available, prefixed with minizinc : - minizinc list solvers - minizinc validate model - minizinc solve model - minizinc solve model by path - minizinc get model info - minizinc get flatzinc Quick sanity check — ask your client: "list the available MiniZinc solvers" . You should see gecode , chuffed , highs , and anything else installed on the machine. | Tool | Description | |---|---| | list solvers | Lists every MiniZinc solver installed on the machine. The returned tag names e.g. gecode , chuffed , highs can be passed to solve model . | | validate model | Parses and type-checks MiniZinc model code without solving it . Useful for checking model syntax up front. Returns VALID or INVALID with an error message. | | solve model | Solves a MiniZinc model given as source code: once, exhaustively all solutions , or with a solution / time limit. Returns the status, solution s , objective value for optimization problems , and solver statistics. | | solve model by path | Same as solve model but loads the model and its optional data .dzn file from paths instead of source code. | | get model info | Inspects a model without solving it : returns its solve method satisfy/minimize/maximize and the declared input parameters and output variables with their types. Useful for an agent to know exactly which params a model expects. | | get flatzinc | Compiles a model and optional data to FlatZinc text without solving it. Returns the .fzn model, the .ozn output model, and flattening statistics. Useful for debugging and low-level inspection. | | Argument | Type | Default | Description | |---|---|---|---| | model code | str | required | The MiniZinc source code .mzn of the model. | | params | dict \| str | None | Parameter assignments like a .dzn file: a JSON object mapping names to values a JSON string encoding such an object is also accepted . | | solver | str | "gecode" | Which solver to use see list solvers . | | all solutions | bool | False | Compute all solutions of a solve satisfy problem. | | max solutions | int \| None | None | Stop after at most this many solutions. | | timeout seconds | int \| None | None | Solver time limit in seconds. | The result is a JSON object like: { "status": "OPTIMAL SOLUTION", "objective": 9, "solution": { "objective": 9, "x": 9, "y": 1 }, "statistics": { "time": 0.204, "nodes": 3, ... } } status is one of SATISFIED , OPTIMAL SOLUTION , ALL SOLUTIONS , UNSATISFIABLE , UNKNOWN , or ERROR . validate model and solve model never raise in normal operation — errors are returned inside the result dict. Clone the repo, then: uv sync create the environment and install mcp + minizinc The server speaks the MCP stdio transport, so it is launched as a subprocess by an MCP client. Run it with the SDK inspector: uv run mcp dev server.py that opens the MCP Inspector in the browser where every tool can be called interactively. A minimal programmatic smoke test: python uv run python -c " import asyncio from mcp import Client from mcp.client.stdio import StdioServerParameters async def main : params = StdioServerParameters command='uv', args= 'run', 'python', 'server.py' , cwd='.' async with Client params as client: result = await client.call tool 'solve model', { 'model code': 'var 1..10: x; var 1..10: y; constraint x + y = 10; solve maximize x;' } print result.content 0 .text asyncio.run main " Install the test dependencies, then run the suite: uv sync --group dev uv run pytest -q The tests in tests/ launch the server end-to-end over stdio and call every tool through the MCP protocol, solving the example model in example/ . They need a working MiniZinc https://www.minizinc.org/ install the same prerequisite as for developers . - params follows JSON representation: JSON arrays map to MiniZinc arrays; numbers, strings, and booleans map to their native MiniZinc types. Exotic types like sets and enums are not fully expressible this way. - Do not combine all solutions with max solutions ; the MiniZinc driver rejects the combination. - MiniZinc requires a solver that supports the model e.g. chuffed / gecode for CP, highs / cbc for MIP models . Use list solvers to see what is installed. - Solutions are returned inline in the tool result; read only hint is set on all tools, so they do not modify your files or system.