Limitless MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Limitless MCP Server what meetings did I have yesterday?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Limitless MCP Server - Enhanced
Overview
A model context protocol (MCP) server that provides advanced analysis of conversations from Limitless Pendant recordings, with intelligent meeting detection, action item extraction, and comprehensive analytics.
What's New in v0.13.0
Complete Pagination Support: ALL tools now properly handle large datasets with pagination
Removed Legacy Features: Cleaned up speech vitality tools to focus on core functionality
Fixed Remaining Tools: Meeting detection, action items, transcripts, and detailed analysis all use pagination
Improved Performance: Consistent 10-item API limit across all tools for optimal performance
Previous Updates (v0.12.0)
Enhanced Token Limit Handling: More aggressive truncation for oversized responses
Fixed Search Tool:
limitless_search_lifelogsnow properly handles token limitsImproved Response Safety: Pre-emptive array truncation before token estimation
Better Error Prevention: All tools now use safe response wrapper consistently
Previous Updates (v0.11.0)
Token Limit Solution: Smart pagination and response chunking to handle large datasets
New Full Transcript Tool:
limitless_get_full_transcriptfetches complete data with automatic paginationEnhanced Pagination: All list tools now support cursor-based pagination to avoid token limits
Intelligent Response Handling: Automatic detection and handling of oversized responses
Multiple Output Formats: Summary, full data, or transcript-only modes for flexibility
Previous Updates (v0.9.0)
Starred Lifelog Support: Filter and identify important conversations marked with stars
Enhanced Error Messages: More specific error handling with detailed context
Improved Timezone Handling: Robust fallback mechanism for timezone detection
Updated Timestamps: Track when lifelogs were last modified with
updatedAtfieldFull API Parity: Now supports 100% of official Limitless API parameters
Related MCP server: limitless-ai-mcp-server
Key Features
Intelligent Meeting Detection: Automatically identifies meetings from conversations
Action Item Extraction: Finds tasks and commitments with context
Natural Language Time Queries: Use expressions like "yesterday", "last week"
Advanced Search: Find conversations across all history with relevance scoring
Daily Summaries: Comprehensive analysis with participants and key topics
Speaker Analytics: Detailed analysis of conversations with specific people
Smart Pagination: Handles large datasets without token limit issues
Raw Transcript Access: Get exact transcripts for further AI processing
Installation
npm install -g 199bio-mcp-limitless-serverUsage
Claude Desktop Configuration
Add to your Claude Desktop MCP settings:
{
"mcpServers": {
"limitless": {
"command": "npx",
"args": ["199bio-mcp-limitless-server"],
"env": {
"LIMITLESS_API_KEY": "your-api-key-here"
}
}
}
}Available Tools
Advanced Analysis Tools
Natural Time Queries:
limitless_get_by_natural_timeMeeting Detection:
limitless_detect_meetingsAction Item Extraction:
limitless_extract_action_itemsDetailed Transcripts:
limitless_get_raw_transcriptDaily Summaries:
limitless_get_daily_summaryFull Transcript Fetcher:
limitless_get_full_transcript(NEW in v0.11.0)
Handling Large Datasets (v0.11.0)
The MCP server now intelligently handles large datasets that would exceed Claude's token limits:
Pagination Support
All list tools now support cursor-based pagination:
# First request
limitless_list_lifelogs_by_date(date="2025-07-24", limit=10)
# Returns: 10 items + cursor
# Next page
limitless_list_lifelogs_by_date(date="2025-07-24", limit=10, cursor="next_page_cursor")Full Transcript Tool
For complete data without manual pagination:
limitless_get_full_transcript(date="2025-07-24", format="transcript_only")Formats available:
summary: Key information only (default)full: Complete data including all fieldstranscript_only: Just the transcript text
API Reference
Core Types
interface Lifelog {
id: string;
title?: string;
markdown?: string;
startTime: string;
endTime: string;
contents?: LifelogContentNode[];
isStarred?: boolean; // NEW: Whether this lifelog is starred
updatedAt?: string; // NEW: When this lifelog was last updated
}
interface LifelogParams {
// ... existing params ...
isStarred?: boolean; // NEW: Filter for starred lifelogs only
batch_size?: number; // NEW: Configurable batch size for performance tuning
}
Development
Building from Source
git clone https://github.com/199-biotechnologies/mcp-limitless-enhanced.git
cd mcp-limitless-enhanced
npm install
npm run buildTesting
# Test with real API data
LIMITLESS_API_KEY=your-key npm run devContributing
We welcome contributions that improve the functionality and reliability of this MCP server.
License
MIT License - see LICENSE file for details.
Troubleshooting
Common Issues
"Claude hit max length" message
This message comes from Claude Desktop's UI when responses are too long or the conversation context is filling up. It's NOT related to:
The MCP server functionality
Your Claude account tier (free/paid)
Limitless API limits
Solution: Start a new conversation or ask for shorter responses.
Server crashes with "Unexpected end of JSON input"
This happens when non-JSON data is sent to the server. MCP servers use JSON-RPC over stdio, not HTTP.
Common mistake: Trying to connect with HTTP clients, browsers, or curl. Solution: Use Claude Desktop or a proper MCP client.
Cannot connect via HTTP/Browser/ngrok
MCP servers are NOT HTTP servers. They communicate via JSON-RPC over stdin/stdout.
Wrong: curl http://localhost:8008
Right: Configure in Claude Desktop's MCP settings
No data returned from queries
As of March 2025, the Limitless API primarily surfaces data from the Limitless Pendant. Ensure:
Your Pendant is actively recording
You have recent conversation data
Your API key has proper permissions
Understanding MCP Servers
What MCP servers ARE:
JSON-RPC services that communicate over stdio
Designed for Claude Desktop and MCP-compatible clients
Tools that extend AI assistant capabilities
What MCP servers are NOT:
HTTP/REST APIs
Web servers
Browser-accessible services
Standalone applications with UIs
If you need HTTP access to Limitless data:
Use the Limitless API directly
Create a separate HTTP wrapper service
Use the official Limitless web interface
Support
Issues: GitHub Issues
Documentation: Scientific Documentation
Contact: boris@199longevity.com
Available Tools
14 toolslimitless_analyze_speakerC
Detailed analytics for conversations with a specific person including speaking time, topics, interaction patterns, and relationship insights.
Inputs: participant_name (required), time_expression, timezone.
limitless_detect_meetingsC
Automatically detect and extract meetings/conversations from lifelogs with intelligent analysis of participants, topics, action items, and key information.
Inputs: time_expression, timezone, min_duration_minutes.
limitless_extract_action_itemsC
Intelligently extract action items and tasks from conversations with context, priority analysis, and smart pattern recognition. Perfect for getting your todo list from meetings.
Inputs: time_expression, timezone, assigned_to, priority.
limitless_get_by_natural_timeA
Get lifelogs using natural time expressions. SUPPORTED: 'today', 'yesterday', 'this week', 'last Monday', 'past 3 days', '2 hours ago'. CONSTRAINTS: limit max 10 per request, use cursor for more. EXAMPLES: time_expression='yesterday', limit=5. NOT SUPPORTED: 'Monday July 14' (use 'July 14 2025' instead).
Inputs: time_expression (required), limit, cursor, timezone, +3 more.
limitless_get_daily_summaryA
Generate daily summary with auto-truncation for token limits. INCLUDES: meetings, action items, participants, topics. CONSTRAINTS: Large responses auto-truncated, use smaller date ranges if needed. ARGS: date (YYYY-MM-DD format, defaults today), timezone (optional). EXAMPLE: date='2025-07-14'.
Inputs: date, timezone.
limitless_get_detailed_analysisB
Deep analysis focused on technical details, exact figures, scientific terminology, and specific information. Preserves precision without generalization - ideal for extracting exact specifications, measurements, and technical discussions.
Inputs: time_expression, timezone, focus_area, preserve_precision.
limitless_get_full_transcriptA
Fetches complete transcript data for a date/range with automatic pagination. Handles large datasets by fetching all pages internally. Use this when you need complete transcript data without worrying about token limits.
Inputs: date, start, end, timezone, +2 more.
limitless_get_lifelog_by_idC
Retrieves a single lifelog or Pendant recording by its specific ID.
Inputs: lifelog_id (required), includeMarkdown, includeHeadings.
limitless_get_raw_transcriptB
Extract clean, unformatted transcripts optimized for AI processing. Preserves technical terminology, scientific terms, and specific details exactly as spoken without markdown formatting or summarization.
Inputs: lifelog_id, time_expression, format, include_timestamps, +4 more.
limitless_list_lifelogs_by_dateA
Lists logs/recordings for a specific date. Returns paginated results to avoid token limits. Use cursor to fetch next page. Best for getting raw log data which you can then analyze for summaries, action items, topics, etc.
Inputs: date (required), limit, cursor, timezone, +4 more.
limitless_list_lifelogs_by_rangeA
Lists logs/recordings within a date/time range. Returns paginated results to avoid token limits. Use cursor to fetch next page. Best for getting raw log data which you can then analyze for summaries, action items, topics, etc.
Inputs: start (required), end (required), limit, cursor, +5 more.
limitless_list_recent_lifelogsA
Lists the most recent logs/recordings (sorted newest first). Returns paginated results to avoid token limits. Use cursor to fetch next page. Best for getting raw log data which you can then analyze for summaries, action items, topics, etc.
Inputs: limit, cursor, timezone, includeMarkdown, +2 more.
limitless_search_conversations_aboutA
Advanced search across ALL lifelogs (not just recent) with intelligent context, relevance scoring, and comprehensive filtering options. Perfect for finding historical discussions.
Inputs: search_term (required), time_expression, speaker_name, content_types, +3 more.
limitless_search_lifelogsA
Performs a simple text search for specific keywords/phrases within the title and content of recent logs/Pendant recordings. Use ONLY for keywords, NOT for concepts like 'action items' or 'summaries'. Searches only recent logs (limited scope).
Inputs: search_term (required), fetch_limit, limit, timezone, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 14 tools
Most tools have distinct purposes, such as analyze_speaker for person-specific analytics, detect_meetings for meeting extraction, and get_by_natural_time for time-based queries. However, there is some overlap between get_full_transcript and get_raw_transcript, as both handle transcript data, which could cause confusion about when to use each.
All tool names follow a consistent verb_noun pattern with the 'limitless_' prefix, such as limitless_analyze_speaker, limitless_detect_meetings, and limitless_get_daily_summary. This uniformity makes the set predictable and easy to navigate.
With 14 tools, the count is well-scoped for a lifelog analysis server, covering key operations like retrieval, analysis, search, and summarization. Each tool serves a clear purpose without feeling excessive or insufficient.
The tool set provides comprehensive coverage for lifelog management, including CRUD-like operations (e.g., get_by_id, list_by_date), analysis (e.g., detailed_analysis, daily_summary), search (e.g., search_conversations_about), and specialized functions (e.g., extract_action_items). No obvious gaps are present for the domain.
Maintenance
Related MCP Connectors
Search and read your recorded meetings, calls, interviews and lectures, with speaker names.
Your Plaud recordings in natural language: list recordings, read speaker-attributed transcripts and
Find recorded calls and meetings, read transcripts, and ask questions grounded in your recordings.
Search and analyze meeting transcripts, summaries, soundbites and analytics from Fireflies.ai
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceConnects AI assistants to your Limitless AI lifelog data, enabling them to search, retrieve, and analyze your recorded conversations and daily activities from your Limitless pendant.16 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with Limitless AI Pendant recordings, search, retrieve, and analyze lifelogs via the Model Context Protocol.16 npm14MIT
- AlicenseNot gradedqualityDmaintenanceEnables querying Gong calls and transcripts through natural language, allowing users to list calls with date filtering and retrieve detailed transcripts with participant context.MIT

SayAll MCPofficial
AlicenseNot gradedqualityDmaintenanceProvides read-only access to local voice-to-text transcription history from the SayAll wireless mic app on macOS. Enables MCP-compatible assistants to query and paginate past transcripts by time and app with strong privacy boundaries.MIT