What are the runtime requirements?
Node.js v16 or higher and a Notion API key from your Notion integrations page.
@ghubnerr
Basic information
A Model Context Protocol (MCP) server for integrating with Notion workspaces (made before the official one 😅)
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"notion": {
"command": "node",
"args": [
"/path/to/notion-mcp-server/build/index.js"
],
"env": {
"NOTION_API_KEY": "your_notion_api_key_here"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
A Model Context Protocol (MCP) server that provides a standardized interface for AI models to access, query, and modify content in Notion workspaces using a Notion API key.
Clone the repository, install dependencies with npm install, create a .env file with your NOTION_API_KEY, build with npm run build, and start with npm start. To use with Claude for Desktop, add the server configuration to the claude_desktop_config.json file.
notion://databasesNode.js v16 or higher and a Notion API key from your Notion integrations page.
Create one at [Notion integrations](https://www.notion.so/my-integrations) and connect it to your workspace with appropriate permissions.
Settings include `DEBUG`, `REQUIRE_CONFIRMATION_FOR_CREATE/UPDATE/DELETE`, `UPDATE_POLLING_INTERVAL`, `MAX_BLOCK_DEPTH`, `BACKUP_DIR`, `BACKUP_RETENTION_DAYS`, and `MAX_BACKUPS_PER_PAGE`.
Add new resources, tools, or prompts in `index.ts`, or enhance API integration in `notion-api.ts`.
Check Claude for Desktop logs (MCP logs) and the server’s standard output and error streams.

Scento Perfume API is a free fragrance API and perfume notes database for developers and AI agents. Search 1,500+ perfumes and 400+ ingredients, compare scents, find similar perfumes, map scent families and build occasio

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.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.
Project context your AI can query through MCP — with source evidence.

Model Context Protocol Servers
Comments