Limitless AI MCP Server

by ericbuess

14 stars
175 downloads
Not rated
GitHub

About

MCP server for integrating Limitless AI Pendant recordings with AI assistants

Details

Author
ericbuess
GitHub stars
14
Downloads
175
Categories
Other

- Full Limitless API integration for Pendant recordings
- Advanced keyword search across recordings
- List recordings by date, date range, or most recent
- Five MCP tools for searching and retrieving lifelogs
- Pre-built prompt templates for common analysis tasks
- Intelligent caching with LRU eviction and configurable TTL

First, obtain a Limitless API key from limitless.ai/developers. Then install either globally from npm (npm install -g limitless-ai-mcp-server) or from source. Configure your MCP client (e.g., Claude Desktop or Claude Code CLI) with the server path and API key environment variable. After configuration, you can chat naturally: “Show me my recordings from today.”

Limitless AI MCP Server

Version
Status
License: MIT
codecov

An advanced Model Context Protocol (MCP) server that enables AI assistants to interact with Limitless AI Pendant recordings. This server provides a seamless bridge between your AI tools and Limitless API, allowing you to extract insights, search through recordings, and analyze your Pendant data.

> ⚠️ Beta Release: This is an early release (v0.0.1). While core features are implemented and tested, we need community feedback to validate all functionality. Please report any issues!

🌟 Features

Core Capabilities

- Full Limitless API Integration: Access all your Pendant recordings programmatically
- Advanced Search: Search through your recordings with keyword matching
- Flexible Querying: List recordings by date, date range, or get recent recordings
- Rich Content Access: Retrieve markdown content, headings, and metadata
- High Performance: Intelligent caching with LRU eviction and TTL support
- Robust Error Handling: Built-in retry logic and timeout management
- Type Safety: Full TypeScript support with comprehensive type definitions

MCP Protocol Implementation

- 🔧 Tools: 5 specialized tools for searching and retrieving recordings
- 📁 Resources: Browse recordings as structured resources with URI navigation
- 📝 Prompts: Pre-built templates for common analysis tasks
- 🔍 Sampling: AI-powered content analysis and summarization
- 🔎 Discovery: Automatic capability exposure to MCP clients

📋 Requirements

- Node.js 22+
- Limitless Pendant (Required - API only returns Pendant recordings)
- Limitless API Key (Get from limitless.ai/developers)
- MCP-compatible client (Claude Desktop, Windsurf, Cursor, etc.)

🏃 Quick Start

1. Get your API key from limitless.ai/developers
2. Clone and build:

   git clone https://github.com/ericbuess/limitless-ai-mcp-server.git
cd limitless-ai-mcp-server
npm install
npm run build

3. Configure Claude Code:
   claude mcp add limitless -s user -e LIMITLESS_API_KEY="your-key" -- node $(pwd)/dist/index.js

4. Start chatting: "Show me my recordings from today"

🚀 Installation

Option 1: Install from npm

npm install -g limitless-ai-mcp-server

Option 2: Install from Source

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.