granola-local-dev-loop

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".

Aller à l'installation

Dépôt: jeremylongshore/tons-of-skills-marketplace
Dernière activité de la source: 19 août 2026 à 12:13
Langue détectée de SKILL.md: anglais
Étoiles: 2 677
Forks: 392

Options d'installation

Le prompt qui vérifie d'abord la source est sélectionné par défaut. Vous pouvez passer à une commande directe ou télécharger une copie locale.

Vérifiez les fichiers source

Lisez SKILL.md et les fichiers associés affichés par SkillsMP avant de décider de l'installer.

Retour à la recherche Retour à l’installation

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 <jeremy@intentsolutions.io>
tags	["saas","granola","workflow","developer"]
compatibility	Designed for Claude Code

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=)[:]:
    ()

// claude_desktop_config.json or .mcp.json
{
  "mcpServers": {
    "granola": {
      "command": "npx",
      "args": ["-y", "granola-mcp-server"]
    }
  }
}

#!/usr/bin/env python3
"""Extract action items from Granola notes and create GitHub issues."""
import json, re, subprocess
from pathlib import Path

def extract_action_items(note_content: str) -> list[dict]:
    """Parse action items from enhanced Granola notes."""
    items = []
    # Matches: - [ ] @person: task description
    pattern = r'- \[ \] @?(\w+):?\s+(.+)'
    for match in re.finditer(pattern, note_content):
        items.append({
            "assignee": match.group(1),
            "task": match.group(2).strip(),
        })
    return items

def create_github_issue(repo: str, title: str, body: str, assignee: str):
    """Create a GitHub issue using gh CLI."""
    cmd = [
        "gh", "issue", "create",
        "--repo", repo,
        "--title", title,
        "--body", body,
        "--assignee", assignee,
    ]
    result = subprocess.run(cmd, capture_output=True, text=True)
    if result.returncode == 0:
        print(f"  Created: {result.stdout.strip()}")
    else:
        print(f"  Error: {result.stderr.strip()}")

# Usage with cache data
cache = load_granola_cache()  # from Step 1
for doc_id, doc in cache["documents"].items():
    content = doc.get("last_viewed_panel", {})
    # ProseMirror content needs text extraction
    text = json.dumps(content)  # simplified — parse nodes for production
    actions = extract_action_items(text)
    for action in actions:
        print(f"[{action['assignee']}] {action['task']}")

#!/bin/bash
set -euo pipefail
# Sync latest Granola meeting notes to project documentation

NOTES_DIR="$HOME/dev/meeting-notes"
mkdir -p "$NOTES_DIR"

# Extract recent meeting titles and dates using Python
python3 -c "
import json
from pathlib import Path

cache_path = Path.home() / 'Library/Application Support/Granola/cache-v3.json'
if cache_path.exists():
    raw = json.loads(cache_path.read_text())
    state = json.loads(raw) if isinstance(raw, str) else raw
    data = state.get('state', state)
    docs = data.get('documents', {})
    for doc_id, doc in sorted(docs.items(),
                              key=lambda x: x[1].get('updated_at', ''),
                              reverse=True)[:5]:
        title = doc.get('title', 'Untitled').replace(' ', '-').lower()
        date = doc.get('created_at', 'unknown')[:10]
        print(f'{date}_{title}')
"

# Reference meeting in commit message
git commit -m "feat: implement user onboarding flow

Per meeting 2026-03-22 'Sprint Planning Q1':
- Agreed on 3-step wizard approach
- Sarah approved the design mockups
- Due by April 15

Action items from Granola note: [link]"

Error	Cause	Fix
Cache file not found	Granola not installed or never launched	Install Granola and capture at least one meeting
JSON parse error	Double-JSON structure not handled	Parse the outer string first, then parse the inner object
MCP server not connecting	Wrong config path	Verify `claude_desktop_config.json` location for your OS
Empty transcripts	Transcript stored separately from document	Check `cache["transcripts"]` keyed by document ID
Stale cache data	Cache not refreshed	Restart Granola to force cache update