systemprompt-mcp-notion
LocalAbout systemprompt-mcp-notion
systemprompt-mcp-notion is an MCP server that lets AI agents access Notion pages, databases and comments through a standard protocol. It is aimed at developers integrating Notion into AI workflows and requires MCP Sampling support to create and update pages.
Key features
- 01Creates and updates pages with rich text formatting
- 02Searches the Notion workspace
- 03TypeScript implementation with Jest test suite
- 04Includes error handling and detailed logging
Use cases
- 01Letting an AI agent create or update Notion pages
- 02Searching workspace content as part of an AI workflow
MCP support
The project is an MCP server that declares resources, tools and prompts capabilities so MCP clients can access Notion content.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEsystemprompt-mcp-notion
SystemPrompt MCP Notion Server
A high-performance Model Context Protocol (MCP) server that seamlessly integrates Notion into your AI workflows. This server enables AI agents to interact with Notion pages and databases through a standardized protocol. This server supports and requires MCP Sampling, which is required to the MCP to create and update Notion pages.
A compatible MCP client is available here.
Server Capabilities
const serverCapabilities: { capabilities: ServerCapabilities } = {
capabilities: {
resources: {
listChanged: true,
},
tools: {},
prompts: {
listChanged: true,
},
sampling: {},
},
};
Key Features
-
📝 Comprehensive Content Management
- Create and update pages with rich text formatting
- Search across your Notion workspace
-
🛠 Developer-Friendly
- Extensive test coverage with Jest
- TypeScript support
- Comprehensive error handling
- Detailed logging and debugging tools
Prerequisites
Before using this server, you'll need:
-
Systemprompt API Key (Free)
- Sign up at systemprompt.io/console
- Create a new API key in your dashboard
-
Notion Account and Workspace
- Active Notion account
- Workspace with content you want to access
-
Notion Integration
- Create at notion.so/my-integrations
- Required capabilities:
- Read/Update/Insert content
- Database management
- Search functionality
-
MCP-Compatible Client
- Systemprompt MCP Client
- Any other MCP-compatible client
Quick Start
-
Installation
Installing via Smithery
To install systemprompt-mcp-notion for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install systemprompt-mcp-notion --client claudenpm install systemprompt-mcp-notion -
Configuration Create a
.envfile:SYSTEMPROMPT_API_KEY=your_systemprompt_api_key NOTION_API_KEY=your_notion_integration_token -
MCP Configuration Add the following to your MCP configuration JSON:
{ "mcpServers": { "notion": { "command": "npx", "args": ["systemprompt-mcp-notion"], "env": { "SYSTEMPROMPT_API_KEY": "your_systemprompt_api_key", "NOTION_API_KEY": "your_notion_integration_token" } } } }Alternatively, if you've installed the package locally:
{ "mcpServers": { "notion": { "command": "node", "args": ["./node_modules/systemprompt-mcp-notion/build/index.js"], "env": { "SYSTEMPROMPT_API_KEY": "your_systemprompt_api_key", "NOTION_API_KEY": "your_notion_integration_token" } } } }
Development
Setup
-
Clone the repository:
git clone https://github.com/systemprompt-io/systemprompt-mcp-notion.git cd systemprompt-mcp-notion -
Install dependencies:
npm install -
Set up environment:
cp .env.example .env # Edit .env with your API keys
Testing
We maintain high test coverage using Jest:
# Run all tests
npm test
# Watch mode for development
npm run test:watch
# Generate coverage report
npm run test:coverage
# Test Notion API connection
npm run test:notion
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.