199bio-mcp-limitless-server
Advanced tools
Scientifically Validated Speech Vitality Index for Limitless Pendant. Empirically validated metrics from 2,500+ conversation segments with transparent reliability assessment. Peer-reviewed methodology for clinical research applications.
A model context protocol (MCP) server that provides scientifically validated analysis of conversational speech patterns from Limitless Pendant recordings. Unlike speculative biomarker approaches, this implementation focuses exclusively on empirically validated metrics derived from real-world transcription data analysis.
updatedAt fieldThis implementation underwent rigorous empirical validation using real Limitless Pendant transcription data:
Micro-responsiveness Rate: Percentage of segments ≤100ms containing responsive words
Turn-taking Velocity: Response time patterns between speakers
Filtered Speaking Rate: Words per minute from validated segments only
Speech Consistency: Variance in speaking patterns within conversations
Conversational Balance: Distribution of speaking time between participants
Speaker Transition Patterns: Frequency and timing of turn-taking
Based on empirical analysis, the following commonly used speech metrics were excluded due to unreliability:
npm install -g 199bio-mcp-limitless-server
Add to your Claude Desktop MCP settings:
{
"mcpServers": {
"limitless": {
"command": "npx",
"args": ["199bio-mcp-limitless-server"],
"env": {
"LIMITLESS_API_KEY": "your-api-key-here"
}
}
}
}
speechclock / speechageGet your scientifically validated Speech Vitality Index.
Parameters:
time_expression (optional): Natural time like "today", "this week", "past 7 days"timezone (optional): IANA timezone for calculationsdetailed (optional): Show detailed component breakdownNote: All lifelog tools now support isStarred parameter to filter only starred conversations.
Example:
What's my speechclock for today?
Response:
Speech Vitality Index: 78/100
Scientifically validated analysis (2.0.0-validated)
Conversation Type: discussion (85% confidence)
Indicators: High responsiveness, Frequent speaker changes
Key Metrics:
• Engagement: 82/100 (18.3% responsiveness)
• Fluency: 76/100 (185 WPM median)
• Interaction: 71/100 (47 transitions)
Data Quality: high (89% confidence)
Duration: 23.4 minutes
limitless_get_by_natural_timelimitless_detect_meetingslimitless_extract_action_itemslimitless_get_raw_transcriptlimitless_get_daily_summaryinterface 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
}
interface ValidatedSpeechVitality {
// Validated metric categories
engagement: EngagementMetrics;
fluency: FluencyMetrics;
interaction: InteractionMetrics;
// Context and reliability
context: ConversationContext;
dataQuality: DataQualityMetrics;
// Composite scores (0-100)
overallScore: number;
engagementScore: number;
fluencyScore: number;
interactionScore: number;
}
Every analysis includes data quality metrics:
interface DataQualityMetrics {
totalSegments: number;
dataReliability: 'high' | 'medium' | 'low';
confidenceScore: number; // 0-100
anomalies: {
unrealisticWPM: number;
suspiciouslyLongGaps: number;
// ... other quality indicators
};
}
git clone https://github.com/199-biotechnologies/mcp-limitless-enhanced.git
cd mcp-limitless-enhanced
npm install
npm run build
# Run empirical validation tests
npm run test:validation
# Test with real API data
LIMITLESS_API_KEY=your-key npm run test:api
We welcome contributions that maintain our scientific rigor:
Djordjevic, B. et al. (2025). "Empirically Validated Speech Pattern Analysis
from Naturalistic Conversation Data: A Model Context Protocol Implementation."
GitHub: 199-biotechnologies/mcp-limitless-enhanced
MIT License - see LICENSE file for details.
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:
Solution: Start a new conversation or ask for shorter responses.
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.
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
As of March 2025, the Limitless API primarily surfaces data from the Limitless Pendant. Ensure:
What MCP servers ARE:
What MCP servers are NOT:
If you need HTTP access to Limitless data:
This implementation prioritizes scientific validity over feature breadth. Every metric included has been empirically validated using real-world data.
FAQs
Scientifically Validated Speech Vitality Index for Limitless Pendant. Empirically validated metrics from 2,500+ conversation segments with transparent reliability assessment. Peer-reviewed methodology for clinical research applications.
The npm package 199bio-mcp-limitless-server receives a total of 64 weekly downloads. As such, 199bio-mcp-limitless-server popularity was classified as not popular.
We found that 199bio-mcp-limitless-server demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Research
North Korean threat actors linked to the Contagious Interview campaign return with 35 new malicious npm packages using a stealthy multi-stage malware loader.
Research
Security News
The Socket Research Team investigates a malicious Python typosquat of a popular password library that forces Windows shutdowns when input is incorrect.
Product
We’ve redesigned the Socket dashboard with simpler navigation, less visual clutter, and a cleaner UI that highlights what really matters.