MCP 服务器

Cursor Notion MCP - Chat Logger

Logs Cursor AI chat interactions to Notion databases for documentation and knowledge management. Captures prompts, responses, context, and timestamps in a structured format for analysis and reference.

README

Cursor Notion MCP - Chat Logger

A Model Context Protocol (MCP) server that logs your Cursor AI chat interactions to Notion for analysis, documentation, and knowledge management.

🌟 Features

✅ Automatic Chat Logging: Log Cursor AI conversations to Notion with a single command
✅ MCP Protocol: Implements the official Model Context Protocol specification
✅ Easy Setup: Simple configuration via environment variables
✅ Rich Context: Captures prompt, response, user, context, and timestamp
✅ Notion Integration: Stores data in a structured Notion database
✅ Privacy First: Self-hosted, no third-party services

📋 Prerequisites

Python 3.7 or higher
Cursor IDE (with MCP support)
Notion account with API access
requests library (pip install requests)

🚀 Quick Start

1. Clone the Repository

git clone https://github.com/Creo-DRB1008/prompt-logger-mcp.git
cd cursor-notion-mcp

2. Install Dependencies

pip install -r requirements.txt

3. Set Up Notion

Create a Notion Integration

Go to Notion Integrations
Click "New integration"
Name it "Cursor Chat Logger"
Copy the Internal Integration Token (starts with secret_)

Create a Notion Database

Create a new database in Notion
Add these properties:
- Prompt (Title) - The user's question
- Response (Text) - The AI's response
- User (Text) - User identifier
- Context (Text) - File/function context
- Timestamp (Date) - When it happened
Share the database with your integration:
- Click "Share" on the database
- Invite your integration

Get the Database ID from the URL:

https://notion.so/YOUR_WORKSPACE/DATABASE_ID?v=...
                                 ^^^^^^^^^^^^

4. Configure Cursor

Edit ~/.cursor/mcp.json (create if it doesn't exist):

{
  "mcpServers": {
    "notion-chat-logger": {
      "command": "python3",
      "args": [
        "/ABSOLUTE/PATH/TO/cursor-notion-mcp/mcp_notion_server.py"
      ],
      "env": {
        "NOTION_API_KEY": "secret_YOUR_NOTION_INTEGRATION_TOKEN",
        "NOTION_DATABASE_ID": "YOUR_DATABASE_ID"
      }
    }
  }
}

Important: Replace:

/ABSOLUTE/PATH/TO/ with the actual path to this repository
secret_YOUR_NOTION_INTEGRATION_TOKEN with your Notion integration token
YOUR_DATABASE_ID with your Notion database ID

5. Restart Cursor

Quit Cursor completely (⌘Q on Mac, Alt+F4 on Windows/Linux) and reopen it.

6. Verify Installation

# Run the test script
python3 test_mcp_notion.py

You should see:

✅ Initialize response
✅ Found 1 tool(s)
✅ Successfully stored to Notion!

💡 Usage

In Cursor Chat

After having a conversation with Cursor AI, simply say:

Log this conversation to Notion

Or use the tool picker:

Type @ in the chat
Select store_chat_log
Fill in the details (or let the AI do it)

Manual Tool Call

You can also invoke the tool explicitly:

@store_chat_log
Prompt: "How do I implement OAuth?"
Response: "Here's how to implement OAuth..."
User: "your.email@example.com"
Context: "auth.py"

🧪 Testing

Quick Verification

./verify_cursor_mcp.sh

Full Test Suite

python3 test_mcp_notion.py

Manual MCP Protocol Test

echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | python3 mcp_notion_server.py

📁 Project Structure

cursor-notion-mcp/
├── mcp_notion_server.py       # Main MCP server
├── test_mcp_notion.py          # Test suite
├── verify_cursor_mcp.sh        # Quick verification script
├── requirements.txt            # Python dependencies
├── README.md                   # This file
├── SETUP.md                    # Detailed setup guide
├── ARCHITECTURE.md             # Technical architecture
└── LICENSE                     # MIT License

🔧 Configuration

Environment Variables

Variable	Required	Description
`NOTION_API_KEY`	Yes	Your Notion integration token
`NOTION_DATABASE_ID`	Yes	Your Notion database ID
`NOTION_VERSION`	No	Notion API version (default: 2022-06-28)

Notion Database Schema

Your Notion database must have these properties:

Property	Type	Description
Prompt	Title	The user's question/prompt
Response	Text	The assistant's response
User	Text	User identifier (email)
Context	Text	File path, function name, etc.
Timestamp	Date	When the interaction occurred

🐛 Troubleshooting

Server Not Showing in Cursor

Check that ~/.cursor/mcp.json is valid JSON
Verify the absolute path to mcp_notion_server.py is correct
Restart Cursor completely (quit and reopen)
Check Cursor logs: ~/Library/Logs/Cursor/ (Mac) or %APPDATA%\Cursor\logs\ (Windows)

Tool Not Appearing

Verify the server is listed in Cursor Settings → Features → MCP
Try typing the full tool name: @store_chat_log
Check Developer Tools (Help → Toggle Developer Tools) for errors

Notion API Errors

Verify your NOTION_API_KEY is correct (starts with secret_)
Verify your NOTION_DATABASE_ID is correct (32 characters, hex)
Ensure the integration has access to the database (Share → Invite integration)
Check that all required properties exist in the database

Python Errors

# Check Python version
python3 --version  # Should be 3.7+

# Install dependencies
pip3 install -r requirements.txt

# Test the server directly
python3 mcp_notion_server.py
# Then type: {"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}

🔐 Security

⚠️ Important Security Notes:

Never commit your Notion API key to version control
Use environment variables for sensitive data
Restrict integration permissions in Notion to only the databases you need
Review logged data regularly to ensure no sensitive information is stored
Consider encrypting sensitive fields before logging

Recommended: Use `.env` File

Instead of hardcoding credentials in mcp.json, use a .env file:

# .env
NOTION_API_KEY=secret_YOUR_TOKEN
NOTION_DATABASE_ID=YOUR_DATABASE_ID

Then update mcp.json:

{
  "mcpServers": {
    "notion-chat-logger": {
      "command": "bash",
      "args": [
        "-c",
        "source .env && python3 /path/to/mcp_notion_server.py"
      ]
    }
  }
}