Limitless MCP Server

Connect AI assistants to Limitless to access personal memory and lifelog data.

Connect AI assistants to your personal memory through Limitless AI's powerful lifelog system. Access your Pendant recordings, meeting notes, and personal insights directly from Claude, Cursor, or any MCP-compatible AI assistant.

# Install globally npm install -g @utlyze/limitless-mcp-server # Or use directly with npx (recommended) npx @utlyze/limitless-mcp-server

{ "mcpServers": { "limitless": { "command": "npx", "args": ["-y", "@utlyze/limitless-mcp-server"], "env": { "LIMITLESS_API_KEY": "your-api-key" } } } }

Limitlessis a personal AI that captures and organizes everything you've seen, said, or heard. Using their Pendant device or desktop app, Limitless creates a searchable memory of your life that you can query and learn from.

npm install -g @utlyze/limitless-mcp-server

npm install @utlyze/limitless-mcp-server

- Sign up atlimitless.ai
- Pair your Pendant or install the desktop app
- Go toWeb App→ Developer → Create API Key

{ "mcpServers": { "limitless": { "command": "npx", "args": ["-y", "@utlyze/limitless-mcp-server"], "env": { "LIMITLESS_API_KEY": "your-api-key-here" } } } }

Add to.cursor/mcp.jsonin your project:

{ "mcpServers": { "limitless": { "command": "npx", "args": ["-y", "@utlyze/limitless-mcp-server"], "env": { "LIMITLESS_API_KEY": "your-api-key-here" } } } }

List your lifelogs with powerful filtering options.

- timezone- Timezone for date filtering (e.g., "America/New_York")
- date- Filter by specific date (YYYY-MM-DD)
- startTime- Start time filter (HH:MM)
- endTime- End time filter (HH:MM)
- limit- Number of results (max 100)
- isStarred- Show only starred lifelogs
- includeMarkdown- Include full markdown content
- direction- Sort order (asc/desc)

Get detailed information about a specific lifelog.

- lifelogId- The ID of the lifelog
- includeMarkdown- Include markdown content
- includeHeadings- Include content structure

Search through your memories using natural language.

- query- Your search query
- dateFrom- Start date for search
- dateTo- End date for search
- source- Filter by source (pendant/desktop/web/mobile)

Get an AI-generated summary of a specific day.

- date- Date to summarize (YYYY-MM-DD)
- timezone- Your timezone
- includeActionItems- Include action items
- includeKeyTopics- Include main topics

Ask questions about your memories and get AI-powered answers.

- query- Your question
- dateFrom- Context start date
- dateTo- Context end date
- includeContext- Include source references

Mark important memories by starring them.

- lifelogId- The lifelog to star/unstar
- isStarred- true to star, false to unstar

Export your memories as formatted markdown.

- date- Export specific date
- dateFrom/dateTo- Export date range
- includeMetadata- Include timestamps and metadata
- groupByDate- Organize by date

"Show me all my memories from yesterday" "What did I discuss in meetings today?" "Find conversations about the product launch" "Get my daily summary for Monday"

"Search for discussions about AI in the last week" "Show me starred memories from December" "Export all my meeting notes from this month" "What action items came up in yesterday's standup?"

"What did John say about the budget proposal?" "When did I last talk about vacation plans?" "Summarize my conversations about the new feature" "What decisions were made in the leadership meeting?"

"Star the memory about the product roadmap" "Export this week's meetings as markdown" "Show me all my Pendant recordings from home"

- Language: TypeScript
- MCP SDK: @modelcontextprotocol/sdk
- HTTP Client: Axios
- Validation: Zod
- Node Version: 16+

src/ ├── config/ # Configuration management ├── lib/ # Core libraries │ ├── limitless-client.ts │ └── logger.ts ├── tools/ # MCP tool implementations │ └── lifelogs/ # Lifelog-related tools └── types/ # TypeScript type definitions

- Comprehensive error messages
- Graceful API failure handling
- Detailed debug logging
- Input validation

- API key validation at startup
- Secure credential handling
- No credential logging
- HTTPS-only communication

# Clone the repository git clone https://github.com/Utlyze/limitless-mcp-server.git cd limitless-mcp-server # Install dependencies npm install # Build the project npm run build # Run tests npm test

- npm run dev- Development mode with hot reload
- npm run build- Build for production
- npm test- Run test suite
- npm run lint- Check code style
- npm run typecheck- Verify TypeScript types

# Run all tests npm test # Run with coverage npm run test:coverage # Run specific test suite npm run test:unit npm run test:integration

- Fork the repository
- Create a feature branch
- Make your changes
- Add tests
- Submit a pull request

- Pendant Only: Currently limited to Pendant recordings (desktop/web coming soon)
- Read Only: No ability to create or modify lifelogs
- Beta API: Some features may change as the API evolves
- Rate Limits: Standard API rate limits apply

- EnsureLIMITLESS_API_KEYis set in your config
- Check that the key is valid and active
- Verify you've created a key at app.limitless.ai

- Ensure you have recordings in your account
- Check the date range you're querying
- Verify your Pendant is syncing properly

- Check your internet connection
- Verify the API is accessible
- Try the debug mode:DEBUG=true

- Restart your AI assistant
- Check the tool name is correct
- Verify MCP server is running

- Documentation:limitless.ai/developers
- Slack Community: Join #developers channel
- GitHub Issues:Report bugs here
- Email:support@limitless.ai

MIT License - seeLICENSEfile for details.

Sync Calendars, Scheduling Links, AI Executive Scheduling Assistant, Unified Calendar