Symbolic Algebra MCP Server

Perform symbolic mathematics and computer algebra using the SymPy library.

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.

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.

$$ m\frac{d^2x}{dt^2} + c\frac{dx}{dt} + kx = F(t) $$

Compute the trace of the Ricci tensor $R_{\mu\nu}$ using the inverse metric $g^{\mu\nu}$ for Anti-de Sitter spacetime to determine its constant scalar curvature $R$.

- 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 theeinsteinpylibrary.

By default variables are predefined with assumptions (similar to how thesymbols()function works in SymPy). Unless otherwise specified the defaut assumptions is that a variable is complex, commutative, term over the complex field $\mathbb{C}$.

{ "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" ] } } }

In your~/.cursor/mcp.json, add the following, whereABSOLUTE_PATH_TO_SYMPY_MCPis 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 and VS Code Insiders now support MCPs inagent mode. For VS Code, you may need to enableChat > Agent: Enablein the settings.

{ "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 switch to agent mode in the chat, and try commands like "integrate x^2" or "solve x^2 = 1" to get started.

To use withCline, 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.

To set up with5ire, 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.pywith the actual path to your sympy-mcp server.py file.

The server supports MCP over HTTP using thestreamable-http transportintroduced in MCP spec 2025-03-26. This replaces the legacy SSE transport and exposes a single/mcpendpoint that clients connect to over HTTP.

# Run locally with HTTP transport uv run python server.py --transport streamable-http # Override host/port uv run python server.py --transport streamable-http --mcp-host 127.0.0.1 --mcp-port 9000

# Build the Docker image docker build -t sympy-mcp . # Run the Docker container docker run -p 8081:8081 sympy-mcp

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

{ "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:main" ] } } }

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.

$$ m\frac{d^2x}{dt^2} + c\frac{dx}{dt} + kx = F(t) $$

Assistant: (Internal tool call)intro_manyto 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_functionto define x(t):

{ "func_name": "x" }

Assistant: (Internal tool call)introduce_expressionto create the differential equation:

{ "expr_str": "Eq(mDerivative(x(t), t, t) + cDerivative(x(t), t) + k*x(t), F(t))" }

Assistant: (Internal tool call)print_latex_expressionto display the equation nicely:

{ "expr_key": "expr_12" }

$$ c \frac{d}{d t} x{\left(t \right)} + k x{\left(t \right)} + m \frac{d^{2}}{d t^{2}} x{\left(t \right)} = F{\left(t \right)} $$

Assistant: (Internal tool call)introduce_functionto define F(t):

{ "func_name": "F" }

Assistant: (Internal tool call)dsolve_odeto solve the differential equation:

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

$$ x{\left(t \right)} = C_{1} e^{\frac{t \left(- c + \sqrt{c^{2} - 4 k m}\right)}{2 m}} + C_{2} e^{- \frac{t \left(c + \sqrt{c^{2} - 4 k m}\right)}{2 m}} + \cdots $$

Example Interaction 2: General Relativity

User: Compute the trace of the Ricci tensor $R_{\mu\nu}$ using the inverse metric $g^{\mu\nu}$ for Anti-de Sitter spacetime to determine its constant scalar curvature $R$.

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

{ "metric_name": "AntiDeSitter" }

Assistant: (Internal tool call)calculate_tensorto calculate the Ricci tensor:

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

Assistant: (Internal tool call)print_latex_tensorto display the Ricci tensor:

{ "tensor_key": "riccitensor_metric_AntiDeSitter" }

$$ \left[\begin{matrix}3 & 0 & 0 & 0\\0 & - 3 \cos^{2}{\left(t \right)} & 0 & 0\\0 & 0 & - 3 \cos^{2}{\left(t \right)} \sinh^{2}{\left(\chi \right)} & 0\\0 & 0 & 0 & - 3 \sin^{2}{\left(\theta \right)} \cos^{2}{\left(t \right)} \sinh^{2}{\left(\chi \right)}\end{matrix}\right] $$

Assistant: (Internal tool call)calculate_tensorto calculate the Ricci scalar: