O'Reilly Learning Platform MCP server

The MCP Server lets you interact with a language model through a simple API for sending queries, retrieving message history, and calling tools. It provides a convenient interface for building applications that need AI-powered text generation and tool execution.

Getting Started

Installation

First, ensure you have the necessary dependencies installed. The server requires Python and the uv package manager. Start the server by running:

uv run client.py http://localhost:8080/sse --api

This will start the MCP server, connecting to an SSE endpoint at localhost:8080/sse.

Using the API

Sending Queries

To send a text query to the model, use the /query endpoint with a POST request:

curl -X POST http://localhost:8000/query \
  -H "Content-Type: application/json" \
  -d '{"text":"Find the top authors on oreilly who write about ai. List their names and the titles of their top books along with links."}'

Retrieving Message History

To get the history of all messages exchanged with the model:

curl http://localhost:8000/messages

This returns a JSON object containing the conversation history.

Calling Tools

The server supports tool execution. To call a specific tool:

curl -X POST http://0.0.0.0:8000/call-tool \
   -H "Content-Type: application/json" \
   -d '{
      "tool_name": "search_content",
      "tool_args": { "query": "python" }}'

In this example, the search_content tool is called with a query for "python".

API Endpoints Summary

• POST /query - Send text queries to the model
• GET /messages - Retrieve message history
• POST /call-tool - Execute a specific tool with arguments

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.