
Mathematical Calculator
STDIOAdvanced mathematical calculation server with symbolic math, statistics, and matrix operations.
Advanced mathematical calculation server with symbolic math, statistics, and matrix operations.
This is a Model Context Protocol (MCP) server that provides Claude with advanced mathematical calculation capabilities, including symbolic math, statistical analysis, and matrix operations.
The Mathematical Calculator MCP Server provides the following tools:
Clone the repository:
git clone https://github.com/huhabla/calculator-mcp-server.git cd calculator-mcp-server
(Option 1) Setup with the provided script:
chmod +x setup_venv.sh ./setup_venv.sh
(Option 2) Or manually set up the virtual environment:
python3 -m venv venv source venv/bin/activate pip install -r requirements.txt
Run doc-tests to verify everything works:
bash run_doctests.sh
To use this MCP server with Claude Desktop:
Make sure you have uv installed (Installation Guide)
Install the MCP server in Claude Desktop:
fastmcp install calculator_server.py
Or with a custom name:
fastmcp install calculator_server.py --name "Math Calculator"
Once installed, Claude will automatically have access to all the mathematical tools and functions.
After integrating with Claude Desktop, you can ask Claude to perform various mathematical operations. Here are some examples:
Can you calculate 3.5^2 * sin(pi/4)?
Solve the following equation: x^2 - 5x + 6 = 0
What's the derivative of sin(x^2) with respect to x?
Calculate the integral of x^2 * e^x
Find the mean, median, mode, and standard deviation of this dataset: [23, 45, 12, 67, 34, 23, 18, 95, 41, 23]
Perform a linear regression on these points: (1,2), (2,3.5), (3,5.1), (4,6.5), (5,8.2)
Multiply these two matrices:
[1, 2, 3]
[4, 5, 6]
and
[7, 8]
[9, 10]
[11, 12]
Run the comprehensive doctest suite:
bash run_doctests.sh
For development and debugging, you can use the FastMCP development mode:
fastmcp dev calculator_server.py
This will start a local web interface where you can test all tools interactively.
This project is licensed under the MIT License - see the LICENSE file for details.