Bayesian Monte Carlo Tree Search
MCTS MCP Server provides a Bayesian Monte Carlo Tree Search engine for AI-assisted analysis and reasoning. It enables Claude to systematically explore different angles and interpretations of topics using a probabilistic approach that balances exploration versus exploitation. The server implements multi-iteration analysis with state persistence between chat turns, approach taxonomy classification, Thompson sampling, surprise detection, and intent classification. It's particularly valuable for users seeking deep, explorative analysis that evolves through multiple iterations, producing insightful analyses that consider diverse philosophical approaches and perspectives.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- search
- Source
- PulseMCP
- Repository
- github.com/angrysky56/mcts-mcp-server
- Author type
- human
- Updated
- 2026-04-28
Use via MCP
Resolve Bayesian Monte Carlo Tree Search from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.