Notion MCP Server
@flyer103
About Notion MCP Server
A simple Notion MCP Server
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"notion-mcp-flyer103": {
"command": "uv",
"args": [
"venv"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Notion MCP Server?
Notion MCP Server implements the Model Context Protocol to interface with Notion’s API, enabling AI models to read and write Notion documents and data. It is built with the official MCP Python SDK and is intended for use with MCP‑compatible LLM clients like Claude for Desktop.
How to use Notion MCP Server?
Clone the repository, create a virtual environment, and install dependencies with uv. Obtain a Notion API key from the Notion integrations page and set it as the NOTION_API_KEY environment variable. Run python -m notion_mcp.server (stdio) or use --transport sse for SSE. For Claude for Desktop, add a claude_desktop_config.json file pointing to the uv executable and the server directory.
Key features of Notion MCP Server
- Supports 14 tools for pages, databases, blocks, comments, and search.
- Two transport methods: stdio (default) and SSE.
- Configured via a single environment variable (
NOTION_API_KEY). - Requires Python 3.12+ and the
uvpackage manager. - Seamlessly integrates with Claude for Desktop through a JSON config file.
Use cases of Notion MCP Server
- Create, read, and update Notion pages via an AI assistant.
- Query and create Notion databases programmatically.
- Append, update, or delete blocks within a page.
- Search across a Notion workspace for objects.
- Add comments to Notion pages through natural language requests.
FAQ from Notion MCP Server
How do I get a Notion API key?
Go to https://www.notion.so/my-integrations, create a new integration, and copy the API key. Then share the relevant Notion pages/databases with the integration by adding it as a connection.
What transport methods are supported?
The server supports standard input/output (stdio) for local clients and Server‑Sent Events (SSE) for web‑based integrations. Use the --transport flag to choose between them.
What are the runtime requirements?
Python 3.12 or higher and the uv package manager are required. All dependencies are installed via uv pip install -e ".[dev]".
How do I integrate it with Claude for Desktop?
Create a claude_desktop_config.json file in the Claude configuration directory with the absolute path to uv, the server directory, and the NOTION_API_KEY environment variable. See the README for exact syntax and platform‑specific paths.
I see a “spawn uv ENOENT” error. How do I fix it?
Claude Desktop cannot find the uv executable. Locate the full path using which uv (macOS/Linux) or where uv (Windows) and use that absolute path in the command field of the configuration file.
More Memory & Knowledge MCP servers
JupyterMCP - Jupyter Notebook Model Context Protocol Integration
jjsantos01A Model Context Protocol (MCP) for Jupyter Notebook
minutes
silversteinEvery meeting, every idea, every voice note — searchable by your AI. Open-source, privacy-first conversation memory layer.
Mcp Knowledge Graph
shanehollomanMCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development
Obsidian MCP Server
cyanheadsRead, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.
Memory Bank MCP Server
alioshrA Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.
Comments