A reasoning engine with multiple strategies, including Beam Search and Monte Carlo Tree Search.
A reasoning implementation for Claude Desktop that lets you use both Beam Search and Monte Carlo Tree Search (MCTS). tbh this started as a way to see if we could make Claude even better at complex problem-solving... turns out we definitely can.
v2.0.0
Added 2 Experimental Reasoning Algorithms:
- `mcts-002-alpha` - Uses the A* Search Method along with an early *alpha* implementation of a Policy Simulation Layer - Also includes an early *alpha* implementation of Adaptive Exploration Simulator & Outcome Based Reasoning Simulator *NOTE* the implementation of these alpha simulators is not complete and is subject to change - `mcts-002alt-alpha` - Uses the Bidirectional Search Method along with an early *alpha* implementation of a Policy Simulation Layer - Also includes an early *alpha* implementation of Adaptive Exploration Simulator & Outcome Based Reasoning Simulator *NOTE* the implementation of these alpha simulators is not complete and is subject to change
What happened to mcts-001-alpha
and mcts-001alt-alpha
?
Quite simply: It was useless and near similar to the base
mcts
method. After initial testing the results yielded in basic thought processes was near similar showing that simply adding policy simulation may not have an effect.
So why add Polciy Simulation Layer now?
Well i think its important to incorporate Policy AND Search in tandem as that is how most of the algorithms implement them.
v1.1.0
Added model control over search parameters:
beamWidth - lets Claude adjust how many paths to track (1-10)
numSimulations - fine-tune MCTS simulation count (1-150)
git clone https://github.com/frgmt0/mcp-reasoner.git
OR clone the original:
git clone https://github.com/Jacck/mcp-reasoner.git
cd mcp-reasoner
npm install
npm run build
Add to Claude Desktop config:
{
"mcpServers": {
"mcp-reasoner": {
"command": "node",
"args": ["path/to/mcp-reasoner/dist/index.js"],
}
}
}
[More Testing Coming Soon]
[Benchmarking will be added soon]
Key Benchmarks to test against:
MATH500
GPQA-Diamond
GMSK8
Maybe Polyglot &/or SWE-Bench
This project is licensed under the MIT License - see the LICENSE file for details.
iOS Swift Package Manager server written in Swift
Securely execute shell commands with whitelisting, resource limits, and timeout controls for LLMs.
A Binary Ninja plugin, MCP server, and bridge that seamlessly integrates Binary Ninja with your favorite MCP client.
A powerful and flexible MCP server designed to enhance the development experience with Shadcn UI components, providing tools for component management, documentation, and installation.
Make your AI agent speak every language on the planet, using Lingo.dev Localization Engine.
An example of a remote MCP server deployable on Cloudflare Workers without authentication.
Official MCP server for Buildable AI-powered development platform. Enables AI assistants to manage tasks, track progress, get project context, and collaborate with humans on software projects.
Analyze large codebases and document collections using high-context models via OpenRouter, OpenAI, or Google AI -- very useful, e.g., with Claude Code
An MCP server and client implementation for the Swagger Petstore API.
Converts LaTeX mathematical expressions to MathML format using MathJax-node.