Uses Pydantic-AI framework to build the math agent with structured data validation and AI model integration
Implements mathematical computation tools including basic arithmetic operations (add, subtract, multiply, divide), power, and logarithm functions through MCP protocol
MathAgent
A minimal math agent that delegates all calculations to an MCP (Model Context Protocol) server. The agent uses MCP tools for every operation—no mental math—so you get consistent, inspectable results.
What’s inside
Agent: built with pydantic-ai, connected via MCP stdio
MCP Server: powered by fastmcp, exposing math tools
Available MCP tools
add
subtract
multiply
divide
power
log
Coming soon:
modulus
Related MCP server: MCP Calculator Server
Requirements
Python 3.13+
uv (Python package/dependency manager)
A Groq API key (for the LLM model)
A Logfire token (for instrumentation)
Setup
Clone the repository
Create your environment file
Set these keys:
groq_key— your Groq API keylogfire_key— your Logfire token
Run the agent
Run with uv so dependencies are resolved and the MCP server is launched as a toolset:
Notes:
The agent is configured to use the Groq model
qwen/qwen3-32b(seeagent.py). You can swap models as needed.The agent will reject non-math questions by design.
All calculations route through the MCP tools defined in
mcp-server.py.
Contributing
Contributions are welcome—feel free to open issues or submit pull requests.