@danhilse
基本信息
A simple MCP integration that allows Claude to read and manage a personal Notion todo list
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"notion_mcp": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
A simple Model Context Protocol (MCP) server that integrates with Notion’s API to manage a personal todo list through Claude. It is tailored for a specific Notion database structure with three properties: Task (title), When (select with only “today” or “later”), and Checkbox (marks completion). This is a personal project intended for a minimalist todo list setup.
Clone the repository, set up a Python 3.10+ virtual environment, install dependencies with uv pip install -e ., create a Notion integration and obtain an API key, share your Notion database with that integration, and place the API key and database ID in a .env file. Configure Claude Desktop by adding the server to claude_desktop_config.json with the command pointing to the project’s virtual environment. Run the server automatically through Claude Desktop (recommended) or manually via python -m notion_mcp. Use natural language commands like “Show all my todos”, “What’s on my list for today?”, “Add a todo for today: check emails”, or “Add a task for later: review project”.
It expects a Notion database with exactly three properties: a title property named “Task”, a select property named “When” with only two options “today” and “later”, and a checkbox property named “Checkbox”. The code is not designed for more complex schemas.
Yes, you can modify the `server.py` file – particularly the `create_todo()` function, the todo formatting in `call_tool()`, and the input schema in `list_tools()` – to match different property names, types, or options.
Python 3.10 or higher, a Notion account, a Notion integration (API key) created at https://www.notion.so/my-integrations, and a Notion database that matches the required structure (or willingness to modify the code).
It only works with the specific database structure described. It has no support for complex schemas, additional properties, recurring tasks, priorities, tags, or advanced error handling. Task scheduling is limited to “today” or “later”.
You can run it directly from the command line with `python -m notion_mcp` after activating the virtual environment, or configure it in Claude Desktop’s `claude_desktop_config.json` so it starts automatically when Claude launches and stops when Claude is closed.
Project context your AI can query through MCP — with source evidence.
AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference
Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.
Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.
评论