Skip to main content

An MCP server that provides basic math operations

Project description

PyPI version Python License


README.md for mcp-math-server

# 📐 MCP Math Server

An [MCP (Model Context Protocol)](https://modelcontextprotocol.io) server that provides basic arithmetic operations — addition, subtraction, multiplication, and division — to integrate easily with LLMs like Claude.

> Built using the official `mcp` Python SDK and `FastMCP`.

---

## 🚀 Features

- ✨ Claude/LLM-ready math tools
- 🔢 Four core operations: add, subtract, multiply, divide
- 🧠 Designed for seamless MCP integration
- 🐍 Easy CLI usage via `mcp-math` command

---

## 📦 Installation

You need Python 3.10 or later.

### Option 1: From PyPI (once published)

```bash
pip install mcp-math-server

Then run:

mcp-math

Option 2: From source (for development)

git clone https://github.com/yourusername/mcp-math-server.git
cd mcp-math-server

# Recommended: use virtualenv or uv
python3 -m venv venv
source venv/bin/activate

pip install -e .
mcp-math

🧪 Usage

After running mcp-math, your server will expose these tools:

🔧 Tools

Tool Description
add Adds two numbers
subtract Subtracts one number from another
multiply Multiplies two numbers
divide Divides one number by another

🤖 Using with Claude Desktop

  1. Download Claude Desktop if you haven’t.
  2. Make sure your MCP server is running via:
mcp-math
  1. In another terminal, register it with Claude:
mcp install $(which mcp-math) --name "Math Assistant"
  1. Claude will now show “Math Assistant” as an available context/tool.

🧠 Example prompt in Claude:

“Use the multiply tool from Math Assistant to calculate 12 × 6.”


🧰 Example MCP Inspector Test

You can also test it manually:

mcp dev mcp_math/server.py

Try calling:

{
  "tool": "divide",
  "arguments": { "x": 100, "y": 5 }
}

📁 Project Structure

mcp-math-server/
├── mcp_math/
│   ├── __init__.py
│   └── server.py  # All MCP logic
├── pyproject.toml  # Package config
├── README.md       # You're reading this

🛠️ Development

Feel free to fork or clone this repo and add more math tools, logging, or context history!

To build & publish to PyPI:

pip install build twine
python -m build
twine upload dist/*

📃 License

MIT © 2025 Ajinkya
See LICENSE for details.


🙌 Contributions Welcome

If you have an idea or improvement, feel free to open an issue or pull request. Let's make LLMs better at math — together!


---

## ✅ Next Steps for You

- ✅ Save this `README.md` to your root folder
- ✅ Replace placeholder fields:
  - `https://github.com/yourusername/...`
  - Your name + email
- ✅ Add a `LICENSE` file (MIT recommended — I can generate one)

---

Would you like me to:
- Create a matching `LICENSE` file?
- Help write a `setup.cfg` or GitHub Actions CI?
- Add more advanced math (e.g. percentages, square roots)?

Let’s keep leveling it up 🚀

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_math_server-0.1.9.tar.gz (3.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_math_server-0.1.9-py3-none-any.whl (4.5 kB view details)

Uploaded Python 3

File details

Details for the file mcp_math_server-0.1.9.tar.gz.

File metadata

  • Download URL: mcp_math_server-0.1.9.tar.gz
  • Upload date:
  • Size: 3.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.1

File hashes

Hashes for mcp_math_server-0.1.9.tar.gz
Algorithm Hash digest
SHA256 6d71243becbba98ff43e47c527f7408fae74d46b07add4c8b03c8f745f712eaa
MD5 1069cc95f42cbd8e6441f07cb9011095
BLAKE2b-256 951440506dadf06a4f661ece949a395118b932293423f2e10baa0a3ae83ce96e

See more details on using hashes here.

File details

Details for the file mcp_math_server-0.1.9-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_math_server-0.1.9-py3-none-any.whl
Algorithm Hash digest
SHA256 5a62f4eedff191a1325c2ed60e79518a00600fff9117bcef82e5c6fdc17722a9
MD5 4e8a87dbf249b50551a909a1706e0b32
BLAKE2b-256 5fe32f05464e9516b55208fd2c29d5774e1676af78cd46766836aca84aaf0f57

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page