granola-local-dev-loop

name	granola-local-dev-loop
description	Access Granola meeting data programmatically for developer workflows. Use when reading notes from the local cache, building MCP integrations, extracting action items into code, or syncing meeting outcomes to dev tools. Trigger: "granola dev workflow", "granola MCP", "granola local cache", "granola developer", "granola programmatic".
allowed-tools	Read, Write, Edit, Bash(curl:*), Bash(jq:*), Bash(python3:*), Grep
version	1.13.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","granola","workflow","developer"]
compatibility	Designed for Claude Code, also compatible with Codex and OpenClaw

Granola Local Dev Loop

Overview

Access Granola meeting data programmatically using three methods: the local cache file (zero-auth, offline), the MCP server (AI agent integration), or the Enterprise API (workspace-wide access). Build developer workflows that turn meeting outcomes into code tasks, documentation, and project artifacts.

Prerequisites

• Granola installed with meetings captured
• Node.js 18+ or Python 3.10+ for scripts
• For MCP: Claude Code, Cursor, or another MCP-compatible client
• For Enterprise API: Business/Enterprise plan + API key

Instructions

Step 1 — Read the Local Cache (Zero Auth)

Granola stores meeting data in a local JSON cache file:

# macOS cache location
CACHE_FILE="$HOME/Library/Application Support/Granola/cache-v3.json"

# Check if cache exists and get size
ls -lh "$CACHE_FILE"

The cache has a double-JSON structure (JSON string inside JSON):

#!/usr/bin/env python3
"""Extract meetings from Granola local cache."""
import json
from pathlib import Path

CACHE_PATH = Path.home() / "Library/Application Support/Granola/cache-v3.json"

def load_granola_cache():
    raw = json.loads(CACHE_PATH.read_text())
    # Cache contains a JSON string that needs secondary parsing
    state = json.loads(raw) if isinstance(raw, str) else raw
    data = state.get("state", state)
    return {
        "documents": data.get("documents", {}),
        "transcripts": data.get("transcripts", {}),
        "meetings_metadata": data.get("meetingsMetadata", {}),
    }

cache = load_granola_cache()
docs = cache[]
()


 doc_id, doc  (docs.items(),
                          key= x: x[].get(, ),
                          reverse=)[:]:
    ()