Skip to main content
Glama
Symbolic Algebra MCP Server
by sdiehl

Symbolic Algebra MCP Server

This library is no longer maintained. It is Apache licensed, so feel free to fork it.

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.

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

Or involving general relativity:

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 $R$.

Related MCP server: ReasonForge

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 $\mathbb{C}$.

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.

  1. One-click Setup:

Install in VS Code

Install in VS Code Insiders

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"
        ]
      }
    }
  }
}
  1. 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.

HTTP Transport (Streamable HTTP / SSE)

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

This is the recommended transport when running the server as a standalone process or in a container, because it allows any HTTP-capable MCP client to connect without needing to launch the server as a subprocess.

# 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

The legacy --transport sse flag is still supported for backward compatibility.

A /healthcheck endpoint is also exposed that runs a full MCP protocol round-trip (initialize → tools/list → session teardown) and returns {"status": "ok", "tool_count": N}.

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

Or use Docker Compose from the docker/ directory:

cd docker
docker compose up -d --build

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

# 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

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: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_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:

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

Assistant: (Internal tool call) introduce_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:

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

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_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:

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

Assistant: (Internal tool call) calculate_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:

$$ -12 $$

Example Interaction 3: Coupled ODE System (Fluid Dynamics)

This example demonstrates solving a coupled system of ODEs and verifying the solution against an algebraic steady-state analysis, a task where LLMs typically hallucinate without a CAS to ground each step.

User:

Use the sympy-mcp tools to solve this symbolically. Do not compute by hand.

Two cylindrical tanks are connected by a pipe. Tank 1 has cross-sectional area A₁ = 2 m² and receives a constant inflow of Q = 0.5 m³/s. Water drains from Tank 1 into Tank 2 through a pipe with flow rate proportional to the height difference: q₁₂ = k·(h₁ - h₂) where k = 0.3 m²/s. Tank 2 has cross-sectional area A₂ = 1 m² and drains to the outside at rate q₂ = k·h₂ with the same k.

Set up and solve the coupled system of ODEs for the water heights h₁(t) and h₂(t), starting from empty tanks (h₁(0) = 0, h₂(0) = 0). Then find the steady-state heights as t → ∞ by solving the equilibrium equations algebraically, and verify they match the long-term solution of the ODEs.

Assistant: (Internal tool chain)

  1. intro_many: introduce t, k, A1, A2, Q with real/positive assumptions

  2. introduce_function × 2: introduce h1(t) and h2(t) as unknown functions

  3. introduce_expression × 2: encode the mass-balance ODEs:

$$A_1 \frac{dh_1}{dt} = Q - k(h_1 - h_2), \quad A_2 \frac{dh_2}{dt} = k(h_1 - h_2) - k h_2$$

  1. substitute_expression: substitute numeric values for k, A1, A2, Q

  2. dsolve_ode × 2: solve the coupled system; apply initial conditions via substitute_expression

  3. introduce_expression × 2: encode equilibrium equations (derivatives set to zero)

  4. solve_linear_system: solve the 2×2 algebraic system for h1*, h2*

  5. print_latex_expression: display both the time-domain solution and the steady-state values

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

Copyright 2025 Stephen Diehl.

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

Available Tools

32 tools
calculate_curlA

Calculates the curl of a vector field using SymPy's curl function.

Args:
    vector_field_key: The key of the vector field expression.

Example:
    # First create a coordinate system
    create_coordinate_system("R")

    # Create a vector field F = (y, -x, 0)
    vector_field = create_vector_field("R", "R_y", "-R_x", "0")

    # Calculate curl
    curl_result = calculate_curl(vector_field)
    # Returns (0, 0, -2)

Returns:
    A key for the curl expression.

Inputs: vector_field_key (required).

calculate_divergenceA

Calculates the divergence of a vector field using SymPy's divergence function.

Args:
    vector_field_key: The key of the vector field expression.

Example:
    # First create a coordinate system
    create_coordinate_system("R")

    # Create a vector field F = (x, y, z)
    vector_field = create_vector_field("R", "R_x", "R_y", "R_z")

    # Calculate divergence
    div_result = calculate_divergence(vector_field)
    # Returns 3

Returns:
    A key for the divergence expression.

Inputs: vector_field_key (required).

calculate_gradientA

Calculates the gradient of a scalar field using SymPy's gradient function.

Args:
    scalar_field_key: The key of the scalar field expression.

Example:
    # First create a coordinate system
    create_coordinate_system("R")

    # Create a scalar field f = x^2 + y^2 + z^2
    scalar_field = introduce_expression("R_x**2 + R_y**2 + R_z**2")

    # Calculate gradient
    grad_result = calculate_gradient(scalar_field)
    # Returns (2x, 2y, 2z)

Returns:
    A key for the gradient vector field expression.

Inputs: scalar_field_key (required).

calculate_tensorC

Calculates a tensor from a metric using einsteinpy.symbolic.

Inputs: metric_key (required), tensor_type (required), simplify_result.

convert_to_unitsA

Converts a quantity to the given target units using sympy.physics.units.convert_to.

Args:
    expr_key: The key of the expression (previously introduced) to convert.
    target_units: List of unit names as strings (e.g., ["meter", "1/second"]).
    unit_system: Optional unit system (from UnitSystem enum). Defaults to SI.

The following units are available by default:
    SI base units: meter, second, kilogram, ampere, kelvin, mole, candela
    Length: kilometer, millimeter
    Mass: gram
    Energy: joule
    Force: newton
    Pressure: pascal
    Power: watt
    Electric: coulomb, volt, ohm, farad, henry
    Constants: speed_of_light, gravitational_constant, planck

IMPORTANT: For compound units like meter/second, you must separate the numerator and
denominator into separate units in the list. For example:
- For meter/second: use ["meter", "1/second"]
- For newton*meter: use ["newton", "meter"]
- For kilogram*meter²/second²: use ["kilogram", "meter**2", "1/second**2"]

Example:
    # Convert speed of light to kilometers per hour
    expr_key = introduce_expression("speed_of_light")
    result = convert_to_units(expr_key, ["kilometer", "1/hour"])
    # Returns approximately 1.08e9 kilometer/hour

    # Convert gravitational constant to CGS units
    expr_key = introduce_expression("gravitational_constant")
    result = convert_to_units(expr_key, ["centimeter**3", "1/gram", "1/second**2"], UnitSystem.CGS)

SI prefixes (femto, pico, nano, micro, milli, centi, deci, deca, hecto, kilo, mega, giga, tera)
can be used directly with base units.

Returns:
    A key for the converted expression, or an error message.

Inputs: expr_key (required), target_units (required), unit_system.

create_coordinate_systemA

Creates a 3D coordinate system for vector calculus operations.

Args:
    name: The name for the coordinate system.
    coord_names: Optional list of coordinate names (3 names for x, y, z).
                If not provided, defaults to [name+'_x', name+'_y', name+'_z'].

Example:
    # Create a coordinate system
    coord_sys = create_coordinate_system("R")
    # Creates a coordinate system R with coordinates R_x, R_y, R_z

    # Create a coordinate system with custom coordinate names
    coord_sys = create_coordinate_system("C", ["rho", "phi", "z"])

Returns:
    The name of the created coordinate system.

Inputs: name (required), coord_names.

create_custom_metricC

Creates a custom metric tensor from provided components and symbols.

Inputs: components (required), symbols (required), config.

create_matrixB

Creates a SymPy matrix from the provided data.

Args:
    matrix_data: A list of lists representing the rows and columns of the matrix.
                Each element can be a number or a string expression.
    matrix_var_name: Optional name for storing the matrix. If not provided, a
                     sequential name will be generated.

Example:
    # Create a 2x2 matrix with numeric values
    matrix_key = create_matrix([[1, 2], [3, 4]], "M")

    # Create a matrix with symbolic expressions (assuming x, y are defined)
    matrix_key = create_matrix([["x", "y"], ["x*y", "x+y"]])

Returns:
    A key for the stored matrix.

Inputs: matrix_data (required), matrix_var_name.

create_predefined_metricC

Creates a predefined spacetime metric.

Inputs: metric_name (required).

create_vector_fieldA

Creates a vector field in the specified coordinate system.

Args:
    coord_sys_name: The name of the coordinate system to use.
    component_x: String expression for the x-component of the vector field.
    component_y: String expression for the y-component of the vector field.
    component_z: String expression for the z-component of the vector field.

Example:
    # First create a coordinate system
    create_coordinate_system("R")

    # Create a vector field F = (y, -x, z)
    vector_field = create_vector_field("R", "R_y", "-R_x", "R_z")

Returns:
    A key for the vector field expression.

Inputs: component_x (required), component_y (required), component_z (required), coord_sys_name (required).

differentiate_expressionA

Differentiates an expression with respect to a variable using SymPy's diff function.

Args:
    expr_key: The key of the expression (previously introduced) to differentiate.
    var_name: The name of the variable to differentiate with respect to.
    order: The order of differentiation (default is 1 for first derivative).

Example:
    # Introduce a variable
    intro("x", [Assumption.REAL], [])

    # Create an expression to differentiate: x^3
    expr_key = introduce_expression("x**3")

    # First derivative
    first_deriv = differentiate_expression(expr_key, "x")
    # Returns 3x²

    # Second derivative
    second_deriv = differentiate_expression(expr_key, "x", 2)
    # Returns 6x

Returns:
    A key for the differentiated expression.

Inputs: expr_key (required), var_name (required), order.

dsolve_odeA

Solves an ordinary differential equation using SymPy's dsolve function.

Args:
    expr_key: The key of the expression (previously introduced) containing the differential equation.
    func_name: The name of the function (previously introduced) to solve for.
    hint: Optional solving method from ODEHint enum. If None, SymPy will try to determine the best method.

Example:
    # First introduce a variable and a function
    intro("x", [Assumption.REAL], [])
    introduce_function("f")

    # Create a second-order ODE: f''(x) + 9*f(x) = 0
    expr_key = introduce_expression("Derivative(f(x), x, x) + 9*f(x)")

    # Solve the ODE
    result = dsolve_ode(expr_key, "f")
    # Returns solution with sin(3*x) and cos(3*x) terms

Returns:
    A LaTeX string representing the solution. Returns an error message string if issues occur.

Inputs: expr_key (required), func_name (required), hint.

integrate_expressionA

Integrates an expression with respect to a variable using SymPy's integrate function.

Args:
    expr_key: The key of the expression (previously introduced) to integrate.
    var_name: The name of the variable to integrate with respect to.
    lower_bound: Optional lower bound for definite integration.
    upper_bound: Optional upper bound for definite integration.

Example:
    # Introduce a variable
    intro("x", [Assumption.REAL], [])

    # Create an expression to integrate: x^2
    expr_key = introduce_expression("x**2")

    # Indefinite integration
    indefinite_result = integrate_expression(expr_key, "x")
    # Returns x³/3

    # Definite integration from 0 to 1
    definite_result = integrate_expression(expr_key, "x", "0", "1")
    # Returns 1/3

Returns:
    A key for the integrated expression.

Inputs: expr_key (required), var_name (required), lower_bound, upper_bound.

introC

Introduces a sympy variable with specified assumptions and stores it.

Takes a variable name and a list of positive and negative assumptions.

Inputs: neg_assumptions (required), pos_assumptions (required), var_name (required).

introduce_expressionA

Parses a sympy expression string using available local variables and stores it. Assigns it to either a temporary name (expr_0, expr_1, etc.) or a user-specified global name.

Uses Sympy parse_expr to parse the expression string.

Applies default Sympy canonicalization rules unless canonicalize is False.

For equations (x^2 = 1) make the input string "Eq(x^2, 1") not "x^2 == 1"

Examples:

    {expr_str: "Eq(x^2 + y^2, 1)"}
    {expr_str: "Matrix(((25, 15, -5), (15, 18, 0), (-5, 0, 11)))"}
    {expr_str: "pi+e", "expr_var_name": "z"}

Inputs: expr_str (required), canonicalize, expr_var_name.

introduce_functionB

Introduces a SymPy function variable and stores it.

Takes a function name and creates a SymPy Function object for use in defining differential equations.

Example:
    {func_name: "f"} will create the function f(x), f(t), etc. that can be used in expressions

Returns:
    The name of the created function.

Inputs: func_name (required).

intro_manyA

Introduces multiple sympy variables with specified assumptions and stores them.

Takes a list of VariableDefinition objects for the 'variables' parameter.
Each object in the list specifies:
- var_name: The name of the variable (string).
- pos_assumptions: A list of positive assumption strings (e.g., ["real", "positive"]).
- neg_assumptions: A list of negative assumption strings (e.g., ["complex"]).

The JSON payload for the 'variables' argument should be a direct list of these objects, for example:
```json
[
    {
        "var_name": "x",
        "pos_assumptions": ["real", "positive"],
        "neg_assumptions": ["complex"]
    },
    {
        "var_name": "y",
        "pos_assumptions": [],
        "neg_assumptions": ["commutative"]
    }
]
```

The assumptions must be consistent, so a real number is not allowed to be non-commutative.

Prefer this over intro() for multiple variables because it's more efficient.

Inputs: variables (required).

matrix_determinantA

Calculates the determinant of a matrix using SymPy's det method.

Args:
    matrix_key: The key of the matrix to calculate the determinant for.

Example:
    # Create a matrix
    matrix_key = create_matrix([[1, 2], [3, 4]])

    # Calculate its determinant
    det_key = matrix_determinant(matrix_key)
    # Results in -2

Returns:
    A key for the determinant expression.

Inputs: matrix_key (required).

matrix_eigenvaluesB

Calculates the eigenvalues of a matrix using SymPy's eigenvals method.

Args:
    matrix_key: The key of the matrix to calculate eigenvalues for.

Example:
    # Create a matrix
    matrix_key = create_matrix([[1, 2], [2, 1]])

    # Calculate its eigenvalues
    evals_key = matrix_eigenvalues(matrix_key)

Returns:
    A key for the eigenvalues expression (usually a dictionary mapping eigenvalues to their multiplicities).

Inputs: matrix_key (required).

matrix_eigenvectorsA

Calculates the eigenvectors of a matrix using SymPy's eigenvects method.

Args:
    matrix_key: The key of the matrix to calculate eigenvectors for.

Example:
    # Create a matrix
    matrix_key = create_matrix([[1, 2], [2, 1]])

    # Calculate its eigenvectors
    evecs_key = matrix_eigenvectors(matrix_key)

Returns:
    A key for the eigenvectors expression (usually a list of tuples (eigenvalue, multiplicity, [eigenvectors])).

Inputs: matrix_key (required).

matrix_inverseA

Calculates the inverse of a matrix using SymPy's inv method.

Args:
    matrix_key: The key of the matrix to invert.

Example:
    # Create a matrix
    matrix_key = create_matrix([[1, 2], [3, 4]])

    # Calculate its inverse
    inv_key = matrix_inverse(matrix_key)

Returns:
    A key for the inverted matrix.

Inputs: matrix_key (required).

pdsolve_pdeA

Solves a partial differential equation using SymPy's pdsolve function.

Args:
    expr_key: The key of the expression (previously introduced) containing the PDE.
             If the expression is not an equation (Eq), it will be interpreted as
             PDE = 0.
    func_name: The name of the function (previously introduced) to solve for.
               This should be a function of multiple variables.

Example:
    # First introduce variables and a function
    intro("x", [Assumption.REAL], [])
    intro("y", [Assumption.REAL], [])
    introduce_function("f")

    # Create a PDE: 1 + 2*(ux/u) + 3*(uy/u) = 0
    expr_key = introduce_expression(
        "Eq(1 + 2*Derivative(f(x, y), x)/f(x, y) + 3*Derivative(f(x, y), y)/f(x, y), 0)"
    )

    # Solve the PDE
    result = pdsolve_pde(expr_key, "f")
    # Returns solution with exponential terms and arbitrary function

Returns:
    A LaTeX string representing the solution. Returns an error message string if issues occur.

Inputs: expr_key (required), func_name (required), hint.

quantity_simplify_unitsA

Simplifies a quantity with units using sympy's built-in simplify method for Quantity objects.

Args:
    expr_key: The key of the expression (previously introduced) to simplify.
    unit_system: Optional unit system (from UnitSystem enum). Not used with direct simplify method.

The following units are available by default:
    SI base units: meter, second, kilogram, ampere, kelvin, mole, candela
    Length: kilometer, millimeter
    Mass: gram
    Energy: joule
    Force: newton
    Pressure: pascal
    Power: watt
    Electric: coulomb, volt, ohm, farad, henry
    Constants: speed_of_light, gravitational_constant, planck

Example:
    # Simplify force expressed in base units
    expr_key = introduce_expression("kilogram*meter/second**2")
    result = quantity_simplify_units(expr_key)
    # Returns newton (as N = kg·m/s²)

    # Simplify a complex expression with mixed units
    expr_key = introduce_expression("joule/(kilogram*meter**2/second**2)")
    result = quantity_simplify_units(expr_key)
    # Returns a dimensionless quantity (1)

    # Simplify electrical power expression
    expr_key = introduce_expression("volt*ampere")
    result = quantity_simplify_units(expr_key)
    # Returns watt

Example with Speed of Light:
    # Introduce the speed of light
    c_key = introduce_expression("speed_of_light")

    # Convert to kilometers per hour
    km_per_hour_key = convert_to_units(c_key, ["kilometer", "1/hour"])

    # Simplify to get the numerical value
    simplified_key = quantity_simplify_units(km_per_hour_key)

    # Print the result
    print_latex_expression(simplified_key)
    # Shows the numeric value of speed of light in km/h

Returns:
    A key for the simplified expression, or an error message.

Inputs: expr_key (required), unit_system.

reset_stateA

Resets the state of the SymPy MCP server.

Clears all stored variables, functions, expressions, metrics, tensors,
coordinate systems, and resets the expression counter.

Then reinitializes unit variables.

Runs after all tool calls for a given computation are done to reset the state for the next computation.

Returns:
    A message confirming the reset.

Inputs: no named parameters.

search_predefined_metricsC

Searches for predefined metrics in einsteinpy.symbolic.predefined.

Inputs: query (required).

simplify_expressionA

Simplifies a mathematical expression using SymPy's simplify function.

Args:
    expr_key: The key of the expression (previously introduced) to simplify.

Example:
    # Introduce variables
    intro("x", [Assumption.REAL], [])
    intro("y", [Assumption.REAL], [])

    # Create an expression to simplify: sin(x)^2 + cos(x)^2
    expr_key = introduce_expression("sin(x)**2 + cos(x)**2")

    # Simplify the expression
    simplified = simplify_expression(expr_key)
    # Returns 1

Returns:
    A key for the simplified expression.

Inputs: expr_key (required).

solve_algebraicallyA

Solves an equation (expression = 0) algebraically for a given variable.

Args:
    expr_key: The key of the expression (previously introduced) to be solved.
    solve_for_var_name: The name of the variable (previously introduced) to solve for.
    domain: The domain to solve in: Domain.COMPLEX, Domain.REAL, Domain.INTEGERS, or Domain.NATURALS. Defaults to Domain.COMPLEX.

Returns:
    A LaTeX string representing the set of solutions. Returns an error message string if issues occur.

Inputs: expr_key (required), solve_for_var_name (required), domain.

solve_linear_systemA

Solves a system of linear equations using SymPy's linsolve.

Args:
    expr_keys: The keys of the expressions (previously introduced) forming the system.
    var_names: The names of the variables to solve for.
    domain: The domain to solve in (Domain.COMPLEX, Domain.REAL, etc.). Defaults to Domain.COMPLEX.

Returns:
    A LaTeX string representing the solution set. Returns an error message string if issues occur.

Inputs: expr_keys (required), var_names (required), domain.

solve_nonlinear_systemA

Solves a system of nonlinear equations using SymPy's nonlinsolve.

Args:
    expr_keys: The keys of the expressions (previously introduced) forming the system.
    var_names: The names of the variables to solve for.
    domain: The domain to solve in (Domain.COMPLEX, Domain.REAL, etc.). Defaults to Domain.COMPLEX.

Returns:
    A LaTeX string representing the solution set. Returns an error message string if issues occur.

Inputs: expr_keys (required), var_names (required), domain.

substitute_expressionA

Substitutes a variable in an expression with another expression using SymPy's subs method.

Args:
    expr_key: The key of the expression to perform substitution on.
    var_name: The name of the variable to substitute.
    replacement_expr_key: The key of the expression to substitute in place of the variable.

Example:
    # Create variables x and y
    intro("x", [], [])
    intro("y", [], [])

    # Create expressions
    expr1 = introduce_expression("x**2 + y**2")
    expr2 = introduce_expression("sin(x)")

    # Substitute y with sin(x) in x^2 + y^2
    result = substitute_expression(expr1, "y", expr2)
    # Results in x^2 + sin^2(x)

Returns:
    A key for the resulting expression after substitution.

Inputs: expr_key (required), replacement_expr_key (required), var_name (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 32 tools

    Disambiguation4/5

    Most tools have distinct purposes, such as calculate_curl for vector calculus, differentiate_expression for derivatives, and solve_algebraically for equation solving. However, there is some overlap between intro and intro_many (both introduce variables) and between the various solve_* tools (linear, nonlinear, algebraic), which could cause minor confusion. Descriptions help clarify, but the boundaries are not perfectly sharp.

    Naming Consistency4/5

    The tool names follow a consistent verb_noun pattern throughout, such as calculate_curl, create_coordinate_system, and simplify_expression. Minor deviations include intro and intro_many (abbreviated verbs) and reset_state (verb_noun but less descriptive), but overall the naming is predictable and readable.

    Tool Count3/5

    With 32 tools, the count feels heavy for a symbolic algebra server, bordering on excessive. While the domain is broad (covering calculus, linear algebra, differential equations, units, etc.), the set includes many specialized tools that might be overwhelming. A more streamlined set of 15-25 tools could improve coherence without losing functionality.

    Completeness5/5

    The tool surface is highly complete for symbolic algebra, covering core operations like differentiation, integration, equation solving (algebraic, linear, nonlinear, ODEs, PDEs), matrix operations (determinant, eigenvalues, inverse), vector calculus (gradient, divergence, curl), unit conversion, and expression manipulation (simplify, substitute). There are no obvious gaps; agents can perform complex workflows from variable introduction to solution output.

    Maintenance

    ActivitySlowing
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides a suite of deterministic math tools powered by SymPy to handle algebra, calculus, linear algebra, and statistics via the Model Context Protocol. It enables smaller language models to delegate complex computations to a verified symbolic backend for accurate and reliable results.
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      A Model Context Protocol server that exposes 8 mathematical tools (arithmetic, algebra, calculus, matrix operations, statistics, probability, unit conversions) to any MCP-compatible AI agent, enabling mathematical computations without code.
      8
      15 npm
      1
      MIT