Symbolic Algebra MCP Server

Integrations

Enables containerized deployment of the MCP server through Docker images
Provides access to the server through GitHub Container Registry for easy deployment
Provides LaTeX rendering of mathematical expressions and tensors for clear visualization of symbolic mathematics

Symbolic Algebra MCP Server

Sympy-MCP is a Model Context Protocol server for allowing LLMs to autonomously perform symbolic mathematics and computer algebra. It exposes numerous tools from SymPy's core functionality to MCP clients for manipulating mathematical expressions and equations.

Why?

Language models are absolutely abysmal at symbolic manipulation. They hallucinate variables, make up random constants, permute terms and generally make a mess. But we have computer algebra systems specifically built for symbolic manipulation, so we can use tool-calling to orchestrate a sequence of transforms so that the symbolic kernel does all the heavy lifting.

While you can certainly have an LLM generate Mathematica or Python code, if you want to use the LLM as an agent or on-the-fly calculator, it's a better experience to use the MCP server and expose the symbolic tools directly.

The server exposes a subset of symbolic mathematics capabilities including algebraic equation solving, integration and differentiation, vector calculus, tensor calculus for general relativity, and both ordinary and partial differential equations.

For example, you can ask it in natural language to solve a differential equation:

Solve the damped harmonic oscillator with forcing term: the mass-spring-damper system described by the differential equation where m is mass, c is the damping coefficient, k is the spring constant, and F(t) is an external force.

Or involving general relativity:

Compute the trace of the Ricci tensor Loading... using the inverse metric Loading... for Anti-de Sitter spacetime to determine its constant scalar curvature Loading....

Usage

You need uv first.

Homebrew - brew install uv
Curl - curl -LsSf https://astral.sh/uv/install.sh | sh

Then you can install and run the server with the following commands:

# Setup the project
git clone https://github.com/sdiehl/sympy-mcp.git
cd sympy-mcp
uv sync

# Install the server to Claude Desktop
uv run mcp install server.py

# Run the server
uv run mcp run server.py

You should see the server available in the Claude Desktop app now. For other clients, see below.

If you want a completely standalone version that just runs with a single command, you can use the following. Note this is running arbitrary code from Github, so be careful.

uv run --with https://github.com/sdiehl/sympy-mcp/releases/download/0.1/sympy_mcp-0.1.0-py3-none-any.whl python server.py

If you want to do general relativity calculations, you need to install the einsteinpy library.

uv sync --group relativity

Available Tools

The sympy-mcp server provides the following tools for symbolic mathematics:

Tool	Tool ID	Description
Variable Introduction	`intro`	Introduces a variable with specified assumptions and stores it
Multiple Variables	`intro_many`	Introduces multiple variables with specified assumptions simultaneously
Expression Parser	`introduce_expression`	Parses an expression string using available local variables and stores it
LaTeX Printer	`print_latex_expression`	Prints a stored expression in LaTeX format, along with variable assumptions
Algebraic Solver	`solve_algebraically`	Solves an equation algebraically for a given variable over a given domain
Linear Solver	`solve_linear_system`	Solves a system of linear equations
Nonlinear Solver	`solve_nonlinear_system`	Solves a system of nonlinear equations
Function Variable	`introduce_function`	Introduces a function variable for use in differential equations
ODE Solver	`dsolve_ode`	Solves an ordinary differential equation
PDE Solver	`pdsolve_pde`	Solves a partial differential equation
Standard Metric	`create_predefined_metric`	Creates a predefined spacetime metric (e.g. Schwarzschild, Kerr, Minkowski)
Metric Search	`search_predefined_metrics`	Searches available predefined metrics
Tensor Calculator	`calculate_tensor`	Calculates tensors from a metric (Ricci, Einstein, Weyl tensors)
Custom Metric	`create_custom_metric`	Creates a custom metric tensor from provided components and symbols
Tensor LaTeX	`print_latex_tensor`	Prints a stored tensor expression in LaTeX format
Simplifier	`simplify_expression`	Simplifies a mathematical expression using SymPy's canonicalize function
Substitution	`substitute_expression`	Substitutes a variable with an expression in another expression
Integration	`integrate_expression`	Integrates an expression with respect to a variable
Differentiation	`differentiate_expression`	Differentiates an expression with respect to a variable
Coordinates	`create_coordinate_system`	Creates a 3D coordinate system for vector calculus operations
Vector Field	`create_vector_field`	Creates a vector field in the specified coordinate system
Curl	`calculate_curl`	Calculates the curl of a vector field
Divergence	`calculate_divergence`	Calculates the divergence of a vector field
Gradient	`calculate_gradient`	Calculates the gradient of a scalar field
Unit Converter	`convert_to_units`	Converts a quantity to given target units
Unit Simplifier	`quantity_simplify_units`	Simplifies a quantity with units
Matrix Creator	`create_matrix`	Creates a SymPy matrix from the provided data
Determinant	`matrix_determinant`	Calculates the determinant of a matrix
Matrix Inverse	`matrix_inverse`	Calculates the inverse of a matrix
Eigenvalues	`matrix_eigenvalues`	Calculates the eigenvalues of a matrix
Eigenvectors	`matrix_eigenvectors`	Calculates the eigenvectors of a matrix

By default variables are predefined with assumptions (similar to how the symbols() function works in SymPy). Unless otherwise specified the defaut assumptions is that a variable is complex, commutative, term over the complex field Loading....

Property	Value
`commutative`	true
`complex`	true
`finite`	true
`infinite`	false

Claude Desktop Setup

Normally the mcp install command will automatically add the server to the claude_desktop_config.json file. If it doesn't you need to find the config file and add the following:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the following to the mcpServers object, replacing /ABSOLUTE_PATH_TO_SYMPY_MCP/server.py with the absolute path to the sympy-mcp server.py file.

{
  "mcpServers": {
    "sympy-mcp": {
      "command": "/opt/homebrew/bin/uv",
      "args": [
        "run",
        "--with",
        "einsteinpy",
        "--with",
        "mcp[cli]",
        "--with",
        "pydantic",
        "--with",
        "sympy",
        "mcp",
        "run",
        "/ABSOLUTE_PATH_TO_SYMPY_MCP/server.py"
      ]
    }
  }
}

Cursor Setup

In your ~/.cursor/mcp.json, add the following, where ABSOLUTE_PATH_TO_SYMPY_MCP is the path to the sympy-mcp server.py file.

{
  "mcpServers": {
    "sympy-mcp": {
      "command": "/opt/homebrew/bin/uv",
      "args": [
        "run",
        "--with",
        "einsteinpy",
        "--with",
        "mcp[cli]",
        "--with",
        "pydantic",
        "--with",
        "sympy",
        "mcp",
        "run",
        "/ABSOLUTE_PATH_TO_SYMPY_MCP/server.py"
      ]
    }
  }
}

VS Code Setup

VS Code and VS Code Insiders now support MCPs in agent mode. For VS Code, you may need to enable Chat > Agent: Enable in the settings.

One-click Setup:

OR manually add the config to your settings.json (global):

{
  "mcp": {
    "servers": {
      "sympy-mcp": {
        "command": "uv",
        "args": [
          "run",
          "--with",
          "einsteinpy",
          "--with",
          "mcp[cli]",
          "--with",
          "pydantic",
          "--with",
          "sympy",
          "mcp",
          "run",
          "/ABSOLUTE_PATH_TO_SYMPY_MCP/server.py"
        ]
      }
    }
  }
}

Click "Start" above the server config, open a Python or math file, switch to agent mode in the chat, and try commands like "integrate x^2" or "solve x^2 = 1" to get started.

Cline Setup

To use with Cline, you need to manually run the MCP server first using the commands in the "Usage" section. Once the MCP server is running, open Cline and select "MCP Servers" at the top.

Then select "Remote Servers" and add the following:

Server Name: sympy-mcp
Server URL: http://127.0.0.1:8081/sse

5ire Setup

Another MCP client that supports multiple models (o3, o4-mini, DeepSeek-R1, etc.) on the backend is 5ire.

To set up with 5ire, open 5ire and go to Tools -> New and set the following configurations:

Tool Key: sympy-mcp
Name: SymPy MCP
Command: /opt/homebrew/bin/uv run --with einsteinpy --with mcp[cli] --with pydantic --with sympy mcp run /ABSOLUTE_PATH_TO/server.py

Replace /ABSOLUTE_PATH_TO/server.py with the actual path to your sympy-mcp server.py file.

Running in Container

You can build and run the server using Docker locally:

# Build the Docker image
docker build -t sympy-mcp .

# Run the Docker container
docker run -p 8081:8081 sympy-mcp

Alternatively, you can pull the pre-built image from GitHub Container Registry:

# Pull the latest image
docker pull ghcr.io/sdiehl/sympy-mcp:latest

# Run the container
docker run -p 8081:8081 --rm ghcr.io/sdiehl/sympy-mcp:latest

To configure Claude Desktop to launch the Docker container, edit your claude_desktop_config.json file:

{
  "mcpServers": {
    "sympy-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "-p",
        "8081:8081",
        "--rm",
        "sympy-mcp"
      ]
    }
  }
}

Or to use the pre-built container from GitHub:

{
  "mcpServers": {
    "sympy-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "-p",
        "8081:8081",
        "--rm",
        "ghcr.io/sdiehl/sympy-mcp:latest"
      ]
    }
  }
}

This configuration tells Claude Desktop to launch the Docker container when needed. Make sure to build the Docker image (docker build -t sympy-mcp .) before using Claude Desktop with this configuration.

The other installation methods can also be adapted to work with Docker if you change the uv command to use the docker run command instead.

Example Interaction 1 : Differential Equations

Here's an example of how the tool-calling works in a conversation with an AI assistant using this MCP server:

User: Solve the damped harmonic oscillator with forcing term: the mass-spring-damper system described by the differential equation where m is mass, c is the damping coefficient, k is the spring constant, and F(t) is an external force.

Assistant: (Internal tool call) intro_many to introduce variables:

{
  "variables": [
    {"var_name": "t", "pos_assumptions": ["real"], "neg_assumptions": []},
    {"var_name": "m", "pos_assumptions": ["real", "positive"], "neg_assumptions": []},
    {"var_name": "c", "pos_assumptions": ["real", "positive"], "neg_assumptions": []},
    {"var_name": "k", "pos_assumptions": ["real", "positive"], "neg_assumptions": []}
  ]
}

Assistant: (Internal tool call) introduce_function to define x(t):

{
  "func_name": "x"
}

Assistant: (Internal tool call) introduce_expression to create the differential equation:

{
  "expr_str": "Eq(m*Derivative(x(t), t, t) + c*Derivative(x(t), t) + k*x(t), F(t))"
}

Assistant: (Internal tool call) print_latex_expression to display the equation nicely:

{
  "expr_key": "expr_12"
}

Result:

Assistant: (Internal tool call) introduce_function to define F(t):

{
  "func_name": "F"
}

Assistant: (Internal tool call) dsolve_ode to solve the differential equation:

{
  "expr_key": "expr_12",
  "func_name": "x"
}

Result:

Example Interaction 2: General Relativity

User: Compute the trace of the Ricci tensor Loading... using the inverse metric Loading... for Anti-de Sitter spacetime to determine its constant scalar curvature Loading....

Assistant: (Internal tool call) create_predefined_metric to create the Anti-de Sitter metric:

{
  "metric_name": "AntiDeSitter"
}

Assistant: (Internal tool call) calculate_tensor to calculate the Ricci tensor:

{
  "metric_key": "metric_AntiDeSitter",
  "tensor_type": "RICCI_TENSOR",
  "simplify_result": true
}

Assistant: (Internal tool call) print_latex_tensor to display the Ricci tensor:

{
  "tensor_key": "riccitensor_metric_AntiDeSitter"
}

Result:

Assistant: (Internal tool call) calculate_tensor to calculate the Ricci scalar:

{
  "metric_key": "metric_AntiDeSitter",
  "tensor_type": "RICCI_SCALAR",
  "simplify_result": true
}

Assistant: (Internal tool call) print_latex_tensor to display the Ricci scalar:

{
  "tensor_key": "ricciscalar_metric_AntiDeSitter"
}

Result:

Security Disclaimer

This server runs on your computer and gives the language model access to run Python logic. Notably it uses Sympy's parse_expr to parse mathematical expressions, which is uses eval under the hood, effectively allowing arbitrary code execution. By running the server, you are trusting the code that Claude generates. Running in the Docker image is slightly safer, but it's still a good idea to review the code before running it.

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.

You must be authenticated.

security – no known vulnerabilities

license - permissive license

quality - confirmed to work

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

Tools

View all tools

A Model Context Protocol server that enables LLMs to autonomously perform symbolic mathematics and computer algebra through SymPy's functionality for manipulating mathematical expressions and equations.

Related Resources

Reddit Discussion about this server

Related MCP Servers

Math-MCP
EthanHenrickson
A
security
A
license
A
quality
A Model Context Protocol server that provides basic mathematical and statistical functions to LLMs, enabling them to perform accurate numerical calculations through a simple API.
Last updated -
13
13
TypeScript
MIT License
Calculator MCP Server
githejie
A
security
A
license
A
quality
A Model Context Protocol server that enables LLMs to perform precise numerical calculations by evaluating mathematical expressions.
Last updated -
1
48
Python
MIT License
Compiler Explorer MCP
torshepherd
-
security
F
license
-
quality
A Model Context Protocol server that connects LLMs to the Compiler Explorer API, enabling them to compile code, explore compiler features, and analyze optimizations across different compilers and languages.
Last updated -
Python
MCP Python Interpreter
yzfly
A
security
F
license
A
quality
A Model Context Protocol server that allows LLMs to interact with Python environments, execute code, and manage files within a specified working directory.
Last updated -
9
8
Python

View all related MCP servers

Symbolic Algebra MCP Server