A Python library for interfacing with Granola.ai meeting data
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"iflow-mcp-pedramamini-granolamcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# GranolaMCP A comprehensive Python library and CLI tool for accessing and analyzing Granola.ai meeting data, featuring a complete MCP (Model Context Protocol) server for AI integration. ## 📋 Changelog ### 2025-07-04 - New Collect Command 🎯 - **NEW**: Added `granola collect` command for exporting your own words from meetings - **FEATURE**: Automatically filters microphone audio (your spoken words) vs system audio (what you heard) - **FEATURE**: Organizes exported text by day into `YYYY-MM-DD.txt` files - **FEATURE**: Supports flexible date ranges (`--last 7d`, `--from/--to`) - **FEATURE**: Optional timestamps and meeting metadata inclusion - **FEATURE**: Minimum word filtering to exclude short utterances - **USE CASE**: Perfect for creating LLM training datasets from your own speech ## Overview GranolaMCP provides complete access to Granola.ai meeting data through multiple interfaces: - **📚 Python Library** - Programmatic access to meetings, transcripts, and summaries - **💻 Command Line Interface** - Rich CLI with advanced filtering and analytics - **🤖 MCP Server** - Model Context Protocol server for AI integration (Claude, etc.) - **📊 Analytics & Visualization** - Comprehensive statistics with ASCII charts ## Data Source **GranolaMCP operates entirely on local cache files** - it reads meeting data directly from Granola's local cache file (`cache-v3.json`) without making any API calls to Granola's servers. This approach provides: - **🔌 No Network Dependency** - Works completely offline - **⚡ Fast Access** - Direct file system access with no API rate limits - **🔒 Privacy Focused** - Your meeting data never leaves your machine - **🛡️ No Authentication** - No need to manage API keys or tokens **Alternative Approach Available:** While not implemented in this library, it's technically possible to extract access tokens from Granola's `supabase.json` configuration file and communicate directly with the Granola API. However, the cache-based approach pr…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.