Paystack MCP Server

This project is a Model Context Protocol server for the Paystack API. It provides a set of tools that can be used by AI assistants and other automated systems to interact with Paystack in a structured way. This allows for the automation of tasks suchs as creating customers, managing products, initiating transactions, and many other tasks.

This server is built using the official paystack-sdk for Python and FastMCP for the server implementation.

Features

• A comprehensive set of tools for interacting with the Paystack API.
• Easy to extend with new tools and functionality.
• Includes a Dockerfile for easy containerization and deployment.

Installation

This project uses uv for dependency management. To install the necessary packages, follow these steps:

1. Clone the repository:

   git clone https://github.com/thisishaykins/paystack-python-mcp
   cd paystack-python-mcp
   

2. Create a virtual environment:

   uv venv
   

3. Activate the virtual environment:

   source .venv/bin/activate
   

4. Install the dependencies:

   uv pip install -e .
   

Setup

To use the Paystack MCP server, you need to provide your Paystack API key. The server is configured to read the API key from an environment variable.

1. Create a .env file in the root of the project.
2. Add your API key to the .env file:

   PAYSTACK_API_KEY=sk_your_secret_key
   

Running the Server

To run the MCP server, execute the following command from the root of the project:

uv run main.py # or python main.py

The server will start and listen for requests on stdio.

Or run using MCP inspector or in dev mode

uv run mcp dev main.py

Available Tools

The following tools are available through the MCP server:

Usage with an AI Assistant (e.g., Claude)

You can connect this MCP server to an AI assistant like Claude to allow it to perform actions on your behalf. The assistant can call the tools by sending a JSON-RPC request to the server.

Usage with Claude Desktop, cursor, or any other Agent

Add the following to your claude_desktop_config.json. See here for more details.

{
  "mcpServers": {
    "paystack": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/paystack-python-mcp",
        "run",
        "main.py"
      ]
    }
  }
}

Here is an example of how Claude could use the customer.create tool:

User: "Please create a new customer with the email address 'test@example.com' and the name 'Test User'."

Claude's Thought Process: "The user wants to create a new customer. I will use the customer.create tool. I need to extract the email, first name, and last name from the user's request."

Claude's Tool Call:

{
  "tool_name": "customer.create",
  "parameters": {
    "email": "test@example.com",
    "first_name": "Test",
    "last_name": "User"
  }
}

The MCP server would then execute the tool and return the result to Claude.

Build using Docker

This project includes a Dockerfile to make it easy to build and run the server in a container.

1. Build the Docker image:

   docker build -t paystack-mcp-server .
   

2. Run the Docker container:

   docker run -it --rm -e PAYSTACK_API_KEY=sk_your_secret_key paystack-mcp-server
   

This will start the server inside a Docker container.

Debugging the Server

To debug your server, you can use the MCP Inspector.

Run the following command in your terminal:

# Start MCP Inspector and server with all tools
uv run mcp dev main.py

Instructions

1. Replace PAYSTACK_API_KEY with your actual Paystack API secret key.
2. Run the command to start the MCP Inspector.
3. Open the MCP Inspector UI in your browser and click Connect to start the MCP server.
4. You can see the list of tools you selected and test each tool individually.

Advanced Usage

This Paystack MCP Server can be extended to covering more primitives, capabilities available on the MCP Server.

MCP Primitives

The MCP protocol defines three core primitives that servers can implement:

Server Capabilities

MCP servers declare capabilities during initialization:

Documentation

• Paystack Python SDK Reference
• Paystack API Reference
• Model Context Protocol API Reference
• Model Context Protocol documentation
• Model Context Protocol specification
• Officially MCP supported servers

Contributing

We are passionate about supporting contributors of all levels of experience and would love to see you get involved in the project. See the contributing guide to get started.

License

This project is licensed under the MIT License - see the LICENSE file for details.