mcpField
M
mcp-sympy

mcp-sympy

Local
github.com/daedalusScience & Education0Updated 27w ago
Repository

About mcp-sympy

mcp-sympy is an MCP server that makes SymPy symbolic mathematics available to MCP clients. It covers algebra, calculus, equation solving, matrices, and other mathematical operations.

Key features

  1. 01Symbolic expression manipulation
  2. 02Differentiation, integration, limits, and series
  3. 03Equation and system solving
  4. 04Matrix operations and eigenvalues
  5. 05Number theory, sets, and logic
  6. 06LaTeX, MathML, and Python output

Use cases

  1. 01Simplifying or factoring symbolic expressions
  2. 02Solving equations and differential equations
  3. 03Computing derivatives, integrals, or limits

MCP support

Exposes SymPy functionality as tools for MCP clients, including symbolic algebra, calculus, solving, matrices, number theory, and output formatting.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "daedalus-mcp-sympy": {
      "command": "uvx",
      "args": [
        "mcp-sympy"
      ]
    }
  }
}
Run commanduvx mcp-sympy

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-sympy0.1.0

Tools

171

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
namesstringYesComma-separated symbol names (e.g., "x, y, z")

Details

From the project README

mcp-sympy

MCP server that exposes SymPy's symbolic mathematics functionality

PyPI Python Coverage Ruff

Install

pip install mcp-sympy

MCP Server

mcp-name: io.github.daedalus/mcp-sympy

Usage

As MCP Server

Configure in your MCP client:

{
  "mcpServers": {
    "mcp-sympy": {
      "command": "mcp-sympy",
      "env": {}
    }
  }
}
Python API
from mcp_sympy import tools

# Simplify expressions
result = tools.sympy_simplify("sin(x)**2 + cos(x)**2")
print(result)  # "1"

# Solve equations
result = tools.sympy_solve("x**2 - 4", "x")
print(result)  # "[2, -2]"

# Differentiate
result = tools.sympy_diff("x**2", "x")
print(result)  # "2*x"

# Integrate
result = tools.sympy_integrate("x**2", "x")
print(result)  # "x**3/3"

# Create matrices
result = tools.sympy_matrix("1,2; 3,4")
print(result)  # "Matrix([[1, 2], [3, 4]])"

# Number theory
result = tools.sympy_isprime("7")
print(result)  # "True"

Available Tools

The MCP server exposes comprehensive SymPy functionality including:

  • Symbolic Expressions: symbols, sympify, simplify, expand, factor
  • Calculus: diff, integrate, limit, series, Derivative, Integral
  • Solving: solve, solveset, nsolve, diophantine, dsolve
  • Matrices: Matrix operations, inverse, determinant, eigenvalues
  • Trigonometry: sin, cos, tan, and their inverses
  • Special Functions: gamma, zeta, erf, fibonacci, etc.
  • Number Theory: isprime, prime, gcd, lcm, totient
  • Sets: FiniteSet, Interval, Union, Intersection
  • Logic: And, Or, Not, Xor
  • Printing: LaTeX, MathML, Python code

Development

git clone https://github.com/daedalus/mcp-sympy.git
cd mcp-sympy
pip install -e ".[test]"

# run tests
pytest

# format
ruff format src/ tests/

# lint
ruff check src/ tests/

# type check
mypy src/

License

MIT License - see LICENSE file.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.