What does Notion MCP Server do?
It acts as a bridge between MCP clients (like Claude Desktop) and Notion’s API, allowing you to perform database queries, page operations, and workspace searches using a standardized protocol.
@ccabanillas
基本信息
A Model Context Protocol (MCP) server implementation for Notion integration, providing a standardized interface for interacting with Notion's API.
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": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@ccabanillas/notion-mcp",
"--client",
"claude"
]
}
}
}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。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
Notion MCP Server is a Model Context Protocol (MCP) server implementation for Notion integration. It provides a standardized interface for interacting with Notion’s API and is compatible with Claude Desktop and other MCP clients.
Install via Smithery (npx -y @smithery/cli install @ccabanillas/notion-mcp --client claude) or manually by cloning the repository, creating a virtual environment, installing dependencies (uv pip install -e . or pip install -e .), and setting a NOTION_API_KEY environment variable in a .env file. Run python -m notion_mcp to test. For Claude Desktop, configure claude_desktop_config.json with the full path to the Python executable and the -m notion_mcp argument.
It acts as a bridge between MCP clients (like Claude Desktop) and Notion’s API, allowing you to perform database queries, page operations, and workspace searches using a standardized protocol.
Go to https://www.notion.so/my-integrations, create a new integration with appropriate read/write capabilities, and copy the token. Then add it as `NOTION_API_KEY` in a `.env` file in the project root.
You need Python (with `uv` or standard `venv`), httpx, Pydantic v2, and MCP 1.6.0. The server uses asynchronous HTTP requests via httpx.
Check that your Notion API key is correct and that you have internet access. Also ensure you have shared the target databases with your integration from the database’s “Share” menu.
The server uses the Model Context Protocol (MCP) over standard input/output (stdio), as shown by the `command` and `args` configuration in `claude_desktop_config.json`.
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Search saved employee handbooks from your AI assistant. Four read-only tools list authorized handbooks, browse policies, search content, and read source pages with citation links. Uses scoped bearer tokens and Streamable

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.

One permissioned folder your team and your AI agents both log into.

The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your
评论