systemprompt -notion
This an Model Context Protocol (MCP) server that integrates Notion into your AI workflows. This server enables seamless access to Notion through MCP, allowing AI agents to interact with pages, databases, and comments.
claude mcp add --transport stdio ejb503-systemprompt-mcp-notion npx -y systemprompt-mcp-notion \ --env NOTION_API_KEY="your_notion_integration_token" \ --env SYSTEMPROMPT_API_KEY="your_systemprompt_api_key"
How to use
SystemPrompt MCP Notion Server exposes Notion integration as an MCP-compliant service. Once running, AI agents can read, create, update, and search Notion pages and databases through the MCP protocol using the provided API keys. The server also supports MCP sampling features for creating and updating Notion content, enabling agents to interact with Notion in a structured, standardized way. To use it with an MCP client, configure the MCP client to connect to the notion server entry (notion) and supply the required environment variables. You can leverage Notion’s pages and databases via the MCP tools and prompts defined by the server capabilities, with robust error handling and logging aiding development and debugging.
How to install
Prerequisites:
- Node.js and npm installed on your machine
- A Systemprompt API key
- A Notion account with an integration token
Option A: Install via Smithery (automatic setup for specific clients)
- Install the server via Smithery for your client, e.g. Claude:
npx -y @smithery/cli install systemprompt-mcp-notion --client claude
Option B: Install as a local npm package
- Install the package locally:
npm install systemprompt-mcp-notion
- Create and configure environment variables in a .env file:
SYSTEMPROMPT_API_KEY=your_systemprompt_api_key
NOTION_API_KEY=your_notion_integration_token
- Add MCP configuration (example):
{
"mcpServers": {
"notion": {
"command": "npx",
"args": ["systemprompt-mcp-notion"],
"env": {
"SYSTEMPROMPT_API_KEY": "your_systemprompt_api_key",
"NOTION_API_KEY": "your_notion_integration_token"
}
}
}
}
- Run the server (depending on your chosen method). If using npx as shown above, ensure the environment variables are loaded in your shell or via your MCP runner.
Additional notes
Notes and tips:
- Ensure your Notion integration has Read/Update/Insert permissions and access to the necessary databases/pages.
- Keep your SystemPrompt API key and Notion integration token secure; avoid committing them to version control.
- If you install locally, you can point the MCP config to the local build index.js as shown in the README: "command": "node", "args": ["./node_modules/systemprompt-mcp-notion/build/index.js"]
- The server supports MCP Sampling and Notion search capabilities; consult the server capabilities section for the exact features enabled in your deployment.
- For debugging, enable verbose logs in your MCP runner and check the server logs for Notion API interactions.
Related MCP Servers
mcp-graphql
Model Context Protocol server for GraphQL
mcp-google-map
A powerful Model Context Protocol (MCP) server providing comprehensive Google Maps API integration with LLM processing capabilities.
systemprompt-code-orchestrator
MCP server for orchestrating AI coding agents (Claude Code CLI & Gemini CLI). Features task management, process execution, Git integration, and dynamic resource discovery. Full TypeScript implementation with Docker support and Cloudflare Tunnel integration.
pluggedin-app
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude, Cursor, etc.) under one roof.
rohlik
MCP server that lets you shop groceries across the Rohlik Group platforms (Rohlik.cz, Knuspr.de, Gurkerl.at, Kifli.hu, Sezamo.ro)
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.