Skip to content
Back to search

mcp-reasoner

A systematic reasoning MCP server implementation for Claude Desktop with beam search and thought evaluation.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/jacck--mcp-reasoner/badge.svg)](/listings/jacck--mcp-reasoner)

HTML

<a href="/listings/jacck--mcp-reasoner"><img src="/api/listings/jacck--mcp-reasoner/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

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

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 97 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # MCP Reasoner
  2. 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.
  3. ### Current Version:
  4. **v2.0.0**
  5. #### What's New:
  6. > Added 2 Experimental Reasoning Algorithms:
  7. >
  8. > - `mcts-002-alpha`
  9. >
  10. > - Uses the A* Search Method along with an early *alpha* implementation of a Policy Simulation Layer
  11. >
  12. > - Also includes an early *alpha* implementation of Adaptive Exploration Simulator & Outcome Based Reasoning Simulator
  13. >
  14. > *NOTE* the implementation of these alpha simulators is not complete and is subject to change
  15. >
  16. > - `mcts-002alt-alpha`
  17. >
  18. > - Uses the Bidirectional Search Method along with an early *alpha* implementation of a Policy Simulation Layer
  19. >
  20. > - Also includes an early *alpha* implementation of Adaptive Exploration Simulator & Outcome Based Reasoning Simulator
  21. >
  22. > *NOTE* the implementation of these alpha simulators is not complete and is subject to change
  23. What happened to `mcts-001-alpha` and `mcts-001alt-alpha`?
  24. > 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.
  25. So why add Polciy Simulation Layer now?
  26. > Well i think its important to incorporate Policy AND Search in tandem as that is how most of the algorithms implement them.
  27. #### Previous Versions:
  28. **v1.1.0**
  29. > Added model control over search parameters:
  30. >
  31. > beamWidth - lets Claude adjust how many paths to track (1-10)
  32. >
  33. > numSimulations - fine-tune MCTS simulation count (1-150)
  34. ## Features
  35. - Two search strategies that you can switch between:
  36. - Beam search (good for straightforward stuff)
  37. - MCTS (when stuff gets complex) with alpha variations (see above)
  38. - Tracks how good different reasoning paths are
  39. - Maps out all the different ways Claude thinks through problems
  40. - Analyzes how the reasoning process went
  41. - Follows the MCP protocol (obviously)
  42. ## Installation
  43. ```
  44. git clone https://github.com/frgmt0/mcp-reasoner.git
  45. OR clone the original:
  46. git clone https://github.com/Jacck/mcp-reasoner.git
  47. cd mcp-reasoner
  48. npm install
  49. npm run build
  50. ```
  51. ## Configuration
  52. Add to Claude Desktop config:
  53. ```
  54. {
  55. "mcpServers": {
  56. "mcp-reasoner": {
  57. "command": "node",
  58. "args": ["path/to/mcp-reasoner/dist/index.js"],
  59. }
  60. }
  61. }
  62. ```
  63. ## Testing
  64. [More Testing Coming Soon]
  65. ## Benchmarks
  66. [Benchmarking will be added soon]
  67. Key Benchmarks to test against:
  68. - MATH500
  69. - GPQA-Diamond
  70. - GMSK8
  71. - Maybe Polyglot &/or SWE-Bench
  72. ## License
  73. This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.