mcpField
N
Notion Knowledge Base MCP Server

Notion Knowledge Base MCP Server

Local
github.com/rickydata-indexerMemory & Knowledge0Updated 94w ago

About Notion Knowledge Base MCP Server

This MCP server lets Cline users query a Notion knowledge base through the Dify API. Responses include detailed information and references to relevant Notion pages.

Key features

  1. 01Query a Notion knowledge base
  2. 02Return detailed answers with page references
  3. 03Provide page links and page IDs
  4. 04Error handling and logging

Use cases

  1. 01Query internal knowledge from Cline
  2. 02Find relevant Notion pages and verify sources

MCP support

The MCP server exposes Notion knowledge-base queries to Cline and accesses the knowledge base through the Dify API.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Notion Knowledge Base MCP Server

An MCP server that provides access to a Notion knowledge base through the Cline VSCode extension.

Features

  • Query your Notion knowledge base directly from Cline
  • Get detailed answers with references to Notion pages
  • Built with FastMCP for reliable performance
  • Comprehensive error handling and logging

Prerequisites

  • Python 3.10 or higher
  • uv package manager
  • Cline VSCode extension
  • A Dify API key for accessing the Notion knowledge base

Installation

  1. Clone this repository:

    git clone https://github.com/yourusername/notion-mcp-server.git
    cd notion-mcp-server
    
  2. Create a .env file with your Dify API key:

    echo "DIFY_API_BACKEND_KEY=your-api-key-here" > .env
    
  3. Install the server in Cline:

    fastmcp install notion_mcp_server.py
    

    This will automatically:

    • Install all required dependencies using uv
    • Configure the server in Cline's settings
    • Make the server available to use with Cline

Usage

Once installed, you can use the server in Cline by asking questions about your Notion knowledge base. For example:

Tell me about internal tooling

The server will respond with relevant information from your Notion knowledge base, including:

  • Detailed answers
  • Links to relevant Notion pages
  • Page IDs for reference

Configuration

The server is configured automatically during installation, but you can manually update the settings in Cline's configuration file if needed:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Example configuration:

{
  "mcpServers": {
    "notion-kb": {
      "command": "uv",
      "args": [
        "run",
        "--with", "fastmcp",
        "--with", "python-dotenv",
        "--with", "requests",
        "fastmcp",
        "run",
        "/absolute/path/to/notion_mcp_server.py"
      ],
      "env": {
        "DIFY_API_BACKEND_KEY": "your-api-key"
      }
    }
  }
}

Development

For development and testing:

  1. Install dependencies:

    pip install -r requirements.txt
    
  2. Run the development server:

    fastmcp dev notion_mcp_server.py
    

This will start the MCP Inspector interface for testing the server.

Troubleshooting

  1. Server not connecting

    • Verify your API key in the .env file
    • Ensure the server path in Cline's config is absolute
    • Check that uv is installed and in your PATH
  2. Dependencies issues

    • Try reinstalling with fastmcp install notion_mcp_server.py --force
    • Verify uv is installed correctly
  3. Server hangs

    • Ensure you're using the uv run command as specified in the config
    • Check the server logs for errors

Contributing

See mcp_instructions.md for detailed information about the server's implementation and architecture.

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.