mcp-reasoner
About
Implements beam search and thought evaluation for structured problem-solving, enabling exploration of multiple solution paths in complex reasoning tasks.
Details
- Author
- Jacck
- Repository
- Jacck/mcp-reasoner
- GitHub stars
- 164
- Downloads
- 1
- License
- MIT License
- Categories
- AI, Developer Tools, Other, Productivity, Design, Search, Frontend, Project Management
- Tags
- #research, #mobile
Jump to
- Two search strategies that you can switch between:
- Beam search (good for straightforward stuff)
- MCTS (when stuff gets complex) with alpha variations (see above)
- Tracks how good different reasoning paths are
- Maps out all the different ways Claude thinks through problems
- Analyzes how the reasoning process went
- Follows the MCP protocol (obviously)
Setting up with Highlight
Follow these steps to add this server as a custom Highlight plugin:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
mcp-reasonerCommand (node, npx, python, etc.)nodeArguments-
Argument 1
path/to/mcp-reasoner/dist/index.js
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Add to Claude Desktop config:
{
"mcpServers": {
"mcp-reasoner": {
"command": "node",
"args": ["path/to/mcp-reasoner/dist/index.js"],
}
}
}
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp-reasoner": {
"cwd": "string",
"env": {},
"args": [
"path/to/mcp-reasoner/dist/index.js"
],
"shell": false,
"command": "node"
}
}
}Linux
{
"cwd": "string",
"env": [],
"args": [
"path/to/mcp-reasoner/dist/index.js"
],
"shell": false,
"command": "node"
}Macos
{
"cwd": "string",
"env": [],
"args": [
"path/to/mcp-reasoner/dist/index.js"
],
"shell": false,
"command": "node"
}Windows
{
"cwd": "string",
"env": [],
"args": [
"path/to/mcp-reasoner/dist/index.js"
],
"shell": false,
"command": "node"
}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.
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 tomcts-001-alphaandmcts-001alt-alpha?
Quite simply: It was useless and near similar to the basemctsmethod. After initial testing the results yielded in basic thought processes was near similar showing that simply adding policy simulation may not have an effect.
Well i think its important to incorporate Policy AND Search in tandem as that is how most of the algorithms implement them.
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)
- Two search strategies that you can switch between:
- Beam search (good for straightforward stuff)
- MCTS (when stuff gets complex) with alpha variations (see above)
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
{ "mcpServers": { "mcp-reasoner": { "command": "node", "args": ["path/to/mcp-reasoner/dist/index.js"], } } }
This project is licensed under the MIT License - see theLICENSEfile for details.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
True deliberative consensus MCP server where AI models debate and refine positions across multiple rounds
MCP server for the Oyemi semantic lexicon. Provides deterministic word-to-code mapping and valence/sentiment analysis for AI agents like Claude, ChatGPT, and Gemini.
Multi-round AI debates between GPT, DeepSeek, Groq, and Claude — all models argue, critique, and synthesize inside your coding assistant.
Advanced cognitive thinking MCP server with DAG-based thought graph, multiple reasoning strategies, metacognition, and self-evaluation.
OpenEnded Philosophy MCP Server with NARS Integration
A philosophical reasoning system combining OpenEnded Philosophy with the Non-Axiomatic Reasoning System (NARS) for advanced analysis and synthesis.
AI Reasoning Cache & Consensus Layer with 50+ reasoning objects across 14 domains. Cache hit/miss with token savings, failure risk check before execution, cross-model verification, and citation tracking. 11 MCP tools via Streamable HTTP.
An advanced MCP server for multi-dimensional, adaptive, and collaborative reasoning.
next-generation MCP reasoning tool. successor to Waldzell AI's Clear Thought.
Predict anything with Chronulus AI forecasting and prediction agents.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
