How do I create a Notion API key?
Go to [Notion Integrations](https://www.notion.so/my-integrations), click “New Integration”, fill in the details, and copy the generated API key. Store it securely.
@grainne-b
基本情報
概要はまだありません
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"notion-mcp-server-grainne-b": {
"command": "uv",
"args": [
"run",
"<your_script.py>"
]
}
}
}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。
Notion_mcp_server is a Model Context Protocol server that enables AI agents such as Claude to interact with Notion via the Notion API. It requires a Notion integration API key, page-level permissions, and the uv Python package manager. This server is designed for developers who want to give LLMs read/write access to Notion pages.
After installing uv (e.g., brew install uv), set up a Notion integration to get an API key, share the target Notion page with that integration, and copy the page ID. Update the PAGE_ID in notion_sdk.py. Run uv run mcp dev server.py to test, or uv run mcp install server.py to register the server with Claude Desktop. The API key must be set as the environment variable NOTION_API_KEY in the Claude configuration.
notion-client Python library.@mcp.tool() decorator.uv package manager to run.Go to [Notion Integrations](https://www.notion.so/my-integrations), click “New Integration”, fill in the details, and copy the generated API key. Store it securely.
Open the target page in Notion, click the “Share” button, invite your integration by name, and ensure it has the required read/write permissions.
The API key must be hardcoded as the `NOTION_API_KEY` environment variable in the MCP server configuration (e.g., `claude_desktop_config.json`). The README explicitly notes that “when installing in Claude, the key needs to be hardcoded”.
The server uses the `notion-client` Python package. The recommended runtime is `uv`, which can be installed via Homebrew. A Python virtual environment may also be used (example shows `.venv` activation).
The server runs over stdio (standard input/output), which is the default transport for MCP servers started with `uv run mcp`. No HTTP or WebSocket transport is mentioned.

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

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

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

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.
コメント