Logic-Thinking MCP Server

Logic-Thinking MCP Server

Enables formal logical reasoning, mathematical problem-solving, and proof construction across 11 logic systems including propositional, predicate, modal, fuzzy, and probabilistic logic. Integrates external solvers (Z3, ProbLog, Clingo) for advanced reasoning, with support for proof storage, argument scoring, and cross-system translation.

Category
Visit Server

README

Logic-Thinking MCP Server

Model Context Protocol server for formal logical reasoning, mathematical problem-solving, verification, and proof construction.

Features

  • 11 logic systems: Syllogistic, Propositional, Predicate, Mathematical, Modal, Temporal, Fuzzy, Deontic, SMT, Probabilistic, ASP
  • External solver integration: Z3 for constraint solving, ProbLog for probabilistic reasoning, Clingo for answer set programming
  • Proof library with persistent storage and full-text search
  • Assumption extraction for detecting hidden assumptions
  • Argument scoring with detailed analysis
  • Batch processing for multiple concurrent requests
  • Cross-system translation between logic systems
  • Contradiction detection
  • Automatic system detection from input
  • Natural language processing with enhanced parsers
  • Visualizations: truth tables, Venn diagrams, Kripke frames, parse trees

Installation

git clone https://github.com/quanticsoul4772/logic-thinking.git
cd logic-thinking
npm install
npm run build

External Solver Dependencies

Three external solvers are used for advanced reasoning capabilities:

  1. Z3 SMT Solver - Install via pip:
pip install z3-solver
  1. ProbLog - Install via pip:
pip install problog
  1. Clingo - Install via pip:
pip install clingo

The server will attempt to use Python from pyenv if available, otherwise falling back to system Python. Ensure your Python environment has these packages installed.

Claude Desktop Integration

Add to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "logic-thinking": {
      "command": "node",
      "args": [
        "--max-old-space-size=4096",
        "--expose-gc",
        "--max-semi-space-size=64",
        "/absolute/path/to/logic-thinking/dist/index.js"
      ]
    }
  }
}

MCP Tools

The server provides 10 tools:

  1. logic-thinking - Core operations (validate, formalize, visualize, solve, score)
  2. logic-batch - Batch processing
  3. logic-translate - Cross-system translation
  4. logic-contradiction - Detect contradictions
  5. logic-proof-save - Save proofs
  6. logic-proof-search - Search proofs
  7. logic-proof-get - Retrieve proof by ID
  8. logic-proof-list - List proofs
  9. logic-proof-stats - Library statistics
  10. logic-extract-assumptions - Extract assumptions

Logic Systems

Syllogistic Logic

Traditional Aristotelian categorical logic.

Propositional Logic

Truth-functional reasoning with logical connectives.

Predicate Logic

First-order logic with quantified statements.

Mathematical Logic

Equation solving, sequence detection, pattern recognition.

Modal Logic

Necessity and possibility with Kripke semantics. Systems: K, T, D, B, K4, KB, S4, S5, KD45

Temporal Logic

Time-based reasoning about sequences and processes.

Fuzzy Logic

Reasoning with degrees of truth and linguistic hedges.

Deontic Logic

Normative reasoning about obligations and permissions.

SMT Logic

Constraint satisfaction and optimization using Z3 theorem prover. Supports integer, real, boolean, and bitvector variables with optimization objectives.

Probabilistic Logic

Probabilistic reasoning using ProbLog. Supports probabilistic facts, rules, evidence-based inference, and probability queries.

ASP (Answer Set Programming)

Non-monotonic reasoning using Clingo. Supports choice rules, constraints, optimization, default reasoning, and stable model enumeration.

License

MIT License - see LICENSE file for details

Author

quanticsoul4772

GitHub: https://github.com/quanticsoul4772

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured