Skip to main content
Glama
Sign In
math-logic-mcp

math-logic-mcp

by ismailkerimov
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

math-logic-mcp

MCP server that gives small LLMs verified symbolic-math & logic tools.

PyPI License

Small language models (Mistral, Llama, Phi, Gemma) struggle with multi-step math and formal logic. Instead of fine-tuning, give them tools. This project exposes a set of verified math and logic solvers via the Model Context Protocol (MCP), so any MCP-compatible LLM can call them as functions.

Features

Tool

What it does

Backend

verify_arithmetic

Safe arithmetic evaluation

Python stdlib (zero deps)

solve_equation

Symbolic equation solving

SymPy (optional)

simplify_expression

Simplify / factor / expand

SymPy (optional)

compute_derivative

Differentiation

SymPy (optional)

compute_integral

Integration

SymPy (optional)

check_logic

SAT / tautology / truth tables

Z3 (optional)

Every result includes proof steps and verification — the LLM gets a machine-checked answer, not a guess.

Related MCP server: Chiasmus

Quick Start

Install from PyPI

pip install math-logic-mcp

Install (full — all solvers)

pip install "math-logic-mcp[full]"

Run the MCP server

# stdio transport (for Claude Desktop, Cursor, etc.)
math-logic-mcp

# HTTP/SSE transport (for remote clients)
math-logic-mcp --http

Configure in Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "math-logic": {
      "command": "math-logic-mcp"
    }
  }
}

Configure in Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "math-logic": {
      "command": "math-logic-mcp"
    }
  }
}

Use as a Python Library

from math_logic import MathLogicEngine

engine = MathLogicEngine()

# Arithmetic (always available)
result = engine.solve("compute 2 + 3 * 4")
print(result.solutions)  # ['14']

# Algebra (requires sympy)
result = engine.solve("Solve x^2 - 4 = 0")
print(result.solutions)  # ['x = -2', 'x = 2']

# Logic (requires z3-solver)
result = engine.solve('Check satisfiability of "p and q"')
print(result.solutions)  # ['Satisfiable: p=True, q=True']

Architecture

LLM ─── MCP Protocol ──▶ mcp_server.py
                              │
                          engine.py  (router → solver → result)
                              │
              ┌───────────────┼───────────────┐
              ▼               ▼               ▼
     ArithmeticSolver   SymPySolver      Z3Solver
      (zero deps)       (pip: sympy)    (pip: z3-solver)

The router classifies each problem by regex patterns and routes to the best available solver. Solvers are loaded lazily — if SymPy isn't installed, algebra problems gracefully report the missing dependency.

Installation Extras

Extra

What it adds

Install size

(none)

Arithmetic only

~1 MB

[sympy]

+ algebra, calculus, simplification

~50 MB

[z3]

+ propositional logic, SAT

~30 MB

[full]

Everything

~80 MB

[dev]

+ pytest, ruff

~85 MB

pip install "math-logic-mcp[sympy]"      # algebra + calculus
pip install "math-logic-mcp[z3]"         # logic
pip install "math-logic-mcp[full]"       # everything
pip install "math-logic-mcp[full,dev]"   # everything + dev tools

Development

git clone https://github.com/ismailkerimov/math-logic-mcp.git
cd math-logic-mcp
pip install -e ".[full,dev]"
pytest tests/ -v

Docker

docker build -t math-logic-mcp .
docker run -p 8080:8080 math-logic-mcp

License

Apache 2.0 — see LICENSE.

Available Tools

6 tools
check_logicCheck LogicA
Read-onlyIdempotent

Check a propositional logic formula for satisfiability, tautology, or generate a truth table.

Inputs: formula (required), check_type. Returns: result

compute_derivativeCompute DerivativeA
Read-onlyIdempotent

Compute the derivative of a mathematical expression with proof steps.

Inputs: expression (required), variable. Returns: result

compute_integralCompute IntegralA
Read-onlyIdempotent

Compute the indefinite integral of a mathematical expression with proof steps.

Inputs: expression (required), variable. Returns: result

simplify_expressionSimplify ExpressionA
Read-onlyIdempotent

Simplify, factor, or expand a mathematical expression with proof steps.

Inputs: expression (required). Returns: result

solve_equationSolve EquationA
Read-onlyIdempotent

Solve an algebraic equation symbolically and return solutions with proof steps.

Inputs: equation (required). Returns: result

verify_arithmeticVerify ArithmeticB
Read-onlyIdempotent

Safely evaluate an arithmetic expression using only whitelisted operators and functions.

Inputs: expression (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    A3.9/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool targets a distinct operation: propositional logic, derivatives, integrals, algebraic simplification, equation solving, and safe arithmetic evaluation. No two tools have overlapping purposes, making selection straightforward.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with underscores, such as check_logic, compute_derivative, and solve_equation. The style is uniform and predictable.

    Tool Count5/5

    With 6 tools, the set is well-scoped for a general math and logic server. It covers core areas without being bloated, balancing comprehensiveness and manageability.

    Completeness3/5

    While fundamental operations are present, notable gaps exist: no predicate logic, no limits or series, no linear algebra or matrix operations, and no statistical functions. This leaves several common math tasks unsupported.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Resources

    Related MCP Connectors

    Related MCP Servers

    • Chiasmus

      yogthos
      A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that gives LLMs access to formal verification via Z3 and SWI-Prolog, plus tree-sitter-based source code analysis. Translates natural language problems into formal logic using a template-based pipeline, verifies results with mathematical certainty, and analyzes call graphs for reachability, dead code, and impact analysis.
      137 npm
      218
      Apache 2.0

    • SymKit

      LBurny
      A
      license
      B
      quality
      B
      maintenance
      MCP server for symbolic computation that enables AI agents to perform step-by-step derivations, transform formulas, and verify results with full provenance, combining natural language with formal mathematical operations.
      41
      13
      Apache 2.0

    • slac-mcp

      DennisPrediger
      A
      license
      Not graded
      quality
      D
      maintenance
      MCP server exposing SLAC (Simple Logic & Arithmetic Compiler) as tools for LLM agents, enabling evaluation of expressions and retrieval of syntax reference.
      Apache 2.0

    Appeared in Searches