Model Context Protocol (MCP) server for constraint optimization and solving"
Model Context Protocol (MCP) server for constraint optimization and solving". Exposed over MCP by the mcp solver mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
An MCP server for constraint solving (SAT, MaxSAT, SMT, CP, ASP, DP). It turns the connected LLM host into a solver-writing agent: the host gets a Python kernel preloaded with a real solver library, modeling instructions for the chosen backend, and a submission gate. The host encodes the problem, runs and verifies it against the real solver, and submits the final program — the outcome is the solution plus the verified solver program that produced it.
Everything the assistant can do here goes through one of these:
Resources — ** mcp-solver://guide (backend selection and workflow) andBackend — Domainpysat — Boolean satisfiability (SAT)maxsat — Weighted optimizationcpmpy — Constraint programming (CP)clingo — Answer Set Programming (ASP)didp — Dynamic programming (DIDP)Execution — Inside the MCP serverVerification — Manual, by the host LLMArtifact — Transient model stateBackends — MiniZinc, PySAT, MaxSAT, Z3, ASPSetup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
You will need one environment variable: OPENROUTER_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
uv run --with) - An OpenRouter API key — for the CLI and benchmark harness only; the MCP server itself runs without onePlenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. MCP Solver's toolset — Resources, Backend, pysat and 8 more — is a fair guide to whether it matches your workflow. It is maintained by szeider; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| Resources | ** mcp-solver://guide (backend selection and workflow) and |
| Backend | Domain |
| pysat | Boolean satisfiability (SAT) |
| maxsat | Weighted optimization |
| cpmpy | Constraint programming (CP) |
| clingo | Answer Set Programming (ASP) |
| didp | Dynamic programming (DIDP) |
| Execution | Inside the MCP server |
| Verification | Manual, by the host LLM |
| Artifact | Transient model state |
| Backends | MiniZinc, PySAT, MaxSAT, Z3, ASP |
{
"mcpServers": {
"mcp-solver": {
"command": "uvx",
"args": ["--from", "mcp-solver[agent]", "mcp-solver-serve"]
}
}
}Configuration as documented by the project. Restart the client after saving.
uv run --with) - An OpenRouter API key — for the CLI and benchmark harness only; the MCP server itself runs without one| Variable | Description | Required |
|---|---|---|
| OPENROUTER_API_KEY | Credential the server authenticates with. | Yes |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.