mcp-reasoner
The MCP Reasoner server provides advanced reasoning capabilities for Claude Desktop with configurable search strategies and parameters.
Multiple reasoning strategies: Choose from Beam Search, Monte Carlo Tree Search (MCTS), and experimental MCTS variations (
mcts_002_alpha,mcts_002_alt_alpha).Customizable parameters:
beamWidth: Control number of reasoning paths (1-10, default: 3)numSimulations: Specify MCTS simulation runs (1-150, default: 50)
Reasoning management:
Track individual thoughts with
thought,thoughtNumber, andtotalThoughtsDetermine if more reasoning steps are needed with
nextThoughtNeeded
Enhanced problem-solving: Optimized for complex scenarios using adaptive algorithms
Process analysis: Map and analyze different reasoning paths
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-reasoner use beam search to solve this logic puzzle"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Reasoner
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.
Current Version:
v2.0.0
What's New:
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
mctsmethod. 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.
Previous Versions:
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)
Features
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)
Related MCP server: MCP Advanced Reasoning Server
Installation
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 buildConfiguration
Add to Claude Desktop config:
{
"mcpServers": {
"mcp-reasoner": {
"command": "node",
"args": ["path/to/mcp-reasoner/dist/index.js"],
}
}
}Testing
[More Testing Coming Soon]
Benchmarks
[Benchmarking will be added soon]
Key Benchmarks to test against:
MATH500
GPQA-Diamond
GMSK8
Maybe Polyglot &/or SWE-Bench
License
This project is licensed under the MIT License - see the LICENSE file for details.
Available Tools
1 toolmcp-reasonerC
Advanced reasoning tool with multiple strategies including Beam Search and Monte Carlo Tree Search
Inputs: nextThoughtNeeded (required), thought (required), thoughtNumber (required), totalThoughts (required), +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'mcp-reasoner' has a clearly distinct purpose focused on advanced reasoning strategies.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The name 'mcp-reasoner' follows a clear, descriptive pattern that matches the server name.
A single tool is generally too few for most server purposes, as it limits functionality and flexibility. While it might be appropriate for a highly specialized niche, the description suggests advanced reasoning with multiple strategies, which could benefit from more granular tools (e.g., separate tools for different search strategies).
It is difficult to assess completeness with only one tool, as there is no clear domain surface to evaluate. The tool covers reasoning strategies, but without additional tools (e.g., for input/output, configuration, or specific reasoning modes), there are likely gaps in a full reasoning workflow.
Maintenance
Related MCP Connectors
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
BeautySpark MCP server for ChatGPT, Claude and other MCP clients
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Hosted Web Crawler MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
Related MCP Servers
- AlicenseCqualityDmaintenanceA systematic reasoning MCP server for Claude Desktop, featuring Beam Search and Monte Carlo Tree Search to facilitate complex problem-solving and decision-making processes.112MIT
- AlicenseDqualityDmaintenanceA Model Context Protocol server that enhances Claude in Cursor AI with advanced reasoning capabilities including Monte Carlo Tree Search, Beam Search, R1 Transformer, and Hybrid Reasoning methods.813ISC
- AlicenseBqualityNot gradedmaintenanceMCP server for structured reasoning with cognitive trap detection, verification, and context compression541 npm1-
- AlicenseNot gradedqualityBmaintenanceAn MCP server that brings difficulty-adaptive, multi-path reasoning to Claude Code. It implements the Actor-Critic-Planner-Reflexion (ACPR) pipeline for deep research synthesis.MIT