What are the prerequisites for using this server?
Python 3.10 or higher, the uv package manager, the Cline VSCode extension, and a Dify API key for accessing the Notion knowledge base.
@rickydata-indexer
基本情報
概要はまだありません
ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
An MCP server that provides access to a Notion knowledge base through the Cline VSCode extension, enabling users to query Notion pages and receive detailed answers with references.
Install prerequisites (Python 3.10+, uv, Cline extension, Dify API key), clone the repository, create a .env file with your Dify API key, then run fastmcp install notion_mcp_server.py. Once installed, ask questions about your Notion knowledge base directly in Cline.
Python 3.10 or higher, the uv package manager, the Cline VSCode extension, and a Dify API key for accessing the Notion knowledge base.
Clone the repository, create a `.env` file with your Dify API key, then run `fastmcp install notion_mcp_server.py`. This installs dependencies and configures the server in Cline automatically.
Edit Cline’s configuration file (macOS: `~/Library/Application Support/Claude/claude_desktop_config.json`, Windows: `%APPDATA%\Claude\claude_desktop_config.json`) with the absolute path to the script and the `DIFY_API_BACKEND_KEY` environment variable.
Verify your API key in the `.env` file, ensure the server path in Cline’s config is absolute, and check that uv is installed and in your PATH. Reinstall with `fastmcp install notion_mcp_server.py --force` if needed.
FastMCP, python-dotenv, and requests. They are installed automatically by uv during the `fastmcp install` command.
Project context your AI can query through MCP — with source evidence.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

Model Context Protocol Servers

The official Semantic-UI-React integration

Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.
コメント