LimitlessSAFE
Advanced MCP Server with AI-powered Limitless API features: natural time queries, meeting detection, action item extraction, daily summaries, and speaker analytics
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
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 limits - Improved 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 pagination - Enhanced 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
updatedAtfield - Full API Parity: Now supp
a48e22941e64OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add 199bio-mcp-limitless-server --env LIMITLESS_API_KEY=${LIMITLESS_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"199bio-mcp-limitless-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"LIMITLESS_API_KEY": "${LIMITLESS_API_KEY}"
}
}
}
}Exposed tools (14)
14 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
limitless_analyze_speaker | read | Detailed analytics for conversations with a specific person including speaking time, topics, interaction patterns, and relationship insights. |
limitless_detect_meetings | read | Automatically detect and extract meetings/conversations from lifelogs with intelligent analysis of participants, topics, action items, and key information. |
limitless_extract_action_items | read | Intelligently extract action items and tasks from conversations with context, priority analysis, and smart pattern recognition. Perfect for getting your todo list from meetings. |
limitless_get_by_natural_time | read | Get lifelogs using natural time expressions. SUPPORTED: |
limitless_get_daily_summary | read | 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= |
limitless_get_detailed_analysis | read | 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. |
limitless_get_full_transcript | read | 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. |
limitless_get_lifelog_by_id | read | Retrieves a single lifelog or Pendant recording by its specific ID. |
limitless_get_raw_transcript | read | Extract clean, unformatted transcripts optimized for AI processing. Preserves technical terminology, scientific terms, and specific details exactly as spoken without markdown formatting or summarization. |
limitless_list_lifelogs_by_date | read | 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. |
limitless_list_lifelogs_by_range | read | 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. |
limitless_list_recent_lifelogs | read | 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. |
limitless_search_conversations_about | read | Advanced search across ALL lifelogs (not just recent) with intelligent context, relevance scoring, and comprehensive filtering options. Perfect for finding historical discussions. |
limitless_search_lifelogs | read | 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 |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
.DS_Store
.DS_Store
zod, @types/node, tsx, typescript
Gates applied: no_behavioural_pass.
a48e22941e64full audit observations/trust-audit/mcp-server/199-mcp__limitless-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | a48e22941e64 | SAFE | B | 89 | first audit |
Questions
What is the Limitless MCP server?
Advanced MCP Server with AI-powered Limitless API features: natural time queries, meeting detection, action item extraction, daily summaries, and speaker analytics
What tools does Limitless expose?
14 in total: 14 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Limitless safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Limitless need?
It reads LIMITLESS_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Limitless run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as 199bio-mcp-limitless-server at 0.13.1.
How current is this page?
The grade is for one exact copy of the source (a48e22941e64), read on 2026-10-09. The repository is watched and re-audited when it changes.