An experimental Model Context Protocol (MCP) server for integrating Granola.ai meeting intelligence with Claude Desktop. This uses Granola's local cache. I don't have any idea how Granola updates or maintains that cache. My guess is that it's doing a rolling context window, but storing long term notes up in AWS. So, YMMV. Use at your own risk. I will likely add a cache shipper at some point since we don't have access to Gronala's data in the cloud.
- Meeting Search: Search meetings by title, content, participants, and transcript content
- Meeting Details: Get comprehensive meeting metadata with local timezone display
- Full Transcript Access: Retrieve complete meeting conversations with speaker identification
- Rich Document Content: Access actual meeting notes, summaries, and structured content
- Pattern Analysis: Analyze patterns across meetings (participants, frequency, topics)
- Timezone Intelligence: All timestamps automatically display in your local timezone
- Real-time Integration: Seamlessly connects to your actual Granola meeting data
- Python 3.12+
- uv package manager
- macOS with Granola.ai installed
- Claude Desktop application
- Granola cache file at
~/Library/Application Support/Granola/cache-v3.json
-
Clone and navigate to the project:
git clone <repository-url> cd granola-ai-mcp
-
Install dependencies with uv:
uv sync
-
Test the installation:
uv run python test_server.py
-
Configure Claude Desktop by adding to your
claude_desktop_config.json
:{ "mcpServers": { "granola": { "command": "uv", "args": ["--directory", "/absolute/path/to/granola-ai-mcp", "run", "granola-mcp-server"], "env": {} } } }
Important: Replace
/absolute/path/to/granola-ai-mcp
with your actual project path. -
Restart Claude Desktop to load the MCP server
Search meetings by query string.
Parameters:
- query (string): Search query for meetings
- limit (integer, optional): Maximum number of results (default: 10)
Get detailed information about a specific meeting.
Parameters:
- meeting_id (string): Meeting ID to retrieve details for
Get transcript for a specific meeting.
Parameters:
- meeting_id (string): Meeting ID to get transcript for
Get documents associated with a meeting.
Parameters:
- meeting_id (string): Meeting ID to get documents for
Analyze patterns across multiple meetings.
Parameters:
- pattern_type (string): Type of pattern to analyze ('topics', 'participants', 'frequency')
- date_range (object, optional): Date range for analysis with start_date and end_date
Once configured with Claude Desktop, you can use natural language to interact with your Granola meetings:
- "Search for meetings about quarterly planning"
- "Show me yesterday's meetings"
- "Find meetings with David from this week"
- "Get the transcript from yesterday's ProofChat meeting"
- "What was discussed in the Float rollback planning meeting?"
- "Show me the full conversation from the David Tibbi meeting"
- "Analyze participant patterns from last month"
- "What documents are associated with the product review meeting?"
- "Search for mentions of 'schema labeling' in meeting transcripts"
The server automatically detects and provides access to:
- Full transcripts from recent meetings (25,000+ characters)
- Meeting content including notes and summaries
- Participant information and speaker identification
- Local timezone display for all meeting times
uv run python test_server.py
uv run granola-mcp-server
uv add package-name
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%\Claude\claude_desktop_config.json
- Linux:
~/.config/Claude/claude_desktop_config.json
The server reads from Granola's cache file at:
~/Library/Application Support/Granola/cache-v3.json
- β 100% Local Processing - All data stays on your machine
- β No External API Calls - No data sent to external services
- β Granola Permissions Respected - Uses existing Granola.ai access controls
- β Read-Only Access - Server only reads from Granola's cache
- Fast Loading: Sub-2 second cache loading for hundreds of meetings
- Rich Content: Extracts 25,000+ character transcripts and meeting notes
- Efficient Search: Multi-field search across titles, content, participants, and transcripts
- Memory Optimized: Lazy loading with intelligent content parsing
- Timezone Smart: Automatic local timezone detection and display
- Production Ready: Successfully processes real Granola data (11.7MB cache files)
- Scalable: Handles large datasets with 500+ transcript segments per meeting
π PRODUCTION READY - Successfully tested with real Granola.ai data including:
- β 39+ meetings parsed and searchable
- β 28 full transcripts with complete conversations
- β Rich meeting content from notes, summaries, and structured data
- β Timezone intelligence showing times like "17:04" instead of "21:04 UTC"
- β Speaker identification and conversation flow
- β Yesterday's meetings fully accessible with detailed content
"Cache file not found"
- Ensure Granola.ai is installed and has processed some meetings
- Check that the cache file exists:
ls -la "~/Library/Application Support/Granola/cache-v3.json"
"uv command not found"
- Install uv:
curl -LsSf https://astral.sh/uv/install.sh | sh
- Or use pip fallback in Claude config:
"command": "python"
"Permission denied"
- Ensure the cache file is readable:
chmod 644 "~/Library/Application Support/Granola/cache-v3.json"
Server not appearing in Claude Desktop
- Verify the absolute path in your Claude config
- Check Claude Desktop logs for MCP server errors
- Restart Claude Desktop after config changes