MCTS MCP Server

MCTS MCP server exists for a simple reason — assistants are far more useful when they can act on MCTS directly instead of describing what you should do. Bayesian MCTS Model Context Protocol Server allowing Claude to control Ollama local models for Advanced MCTS and analysis.

What you get

A Model Context Protocol (MCP) server that exposes an Advanced Bayesian Monte Carlo Tree Search (MCTS) engine for AI-assisted analysis and reasoning.

This MCP server enables Claude to use Monte Carlo Tree Search (MCTS) algorithms for deep, explorative analysis of topics, questions, or text inputs. The MCTS algorithm uses a Bayesian approach to systematically explore different angles and interpretations, producing insightful analyses that evolve through multiple iterations.

• Bayesian MCTS — Uses a probabilistic approach to balance exploration vs. exploitation during analysis
• Multi-iteration Analysis — Supports multiple iterations of thinking with multiple simulations per iteration
• State Persistence — Remembers key results, unfit approaches, and priors between turns in the same chat
• Approach Taxonomy — Classifies generated thoughts into different philosophical approaches and families
• Thompson Sampling — Can use Thompson sampling or UCT for node selection
• Surprise Detection — Identifies surprising or novel directions of analysis

What the assistant can call

Once MCTS is connected, these are the calls the assistant has available:

• initialize_mcts — Start a new MCTS analysis with a specific question. Can optionally specify provider_name and model_name to override defaults for this run
• run_mcts — Run the MCTS algorithm for a set number of iterations/simulations
• generate_synthesis — Generate a final summary of the MCTS results
• get_config — View current MCTS configuration parameters, including active LLM provider and model
• update_config — Update MCTS configuration parameters (excluding provider/model, use set_active_llm for that)
• get_mcts_status — Check the current status of the MCTS system
• Prerequisites — The Prerequisites tool exposed by this server

Setting it up

google-genai on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Configuration and credentials

You will need 4 environment variables: UV_PROJECT_ENVIRONMENT, OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_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.

• Python 3.10+ (required) - Internet connection (for downloading dependencies)

Choosing this one

Plenty 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. MCTS's toolset — initialize_mcts, run_mcts, generate_synthesis and 4 more — is a fair guide to whether it matches your workflow. It is maintained by angrysky56; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
• MCP clients confirm each tool call by default. Leave that on until you have watched what the mcts mcp server does with a few real requests.