looker-studio-mcp
Automates Looker Studio dashboards using Playwright, enabling creation, modification, screenshots, and exports.
README
đŻ Looker Studio MCP (Model Context Protocol)
Automatisation de Looker Studio via Playwright â crĂ©ation, modification, et gestion de dashboards.
đ FonctionnalitĂ©s
- â Login Google automatisĂ© avec profil persistant
- â CrĂ©ation de rapports Looker Studio
- â Ajout de sources (Google Sheets, BigQuery, etc.)
- â Ajout de graphiques (Scorecard, Table, Time Series, etc.)
- â Screenshots de dashboards
- â Export CSV des donnĂ©es
- â Listage des rapports existants
- â Mode interactif avec CLI
đŠ Installation
# Cloner le repo
git clone https://github.com/ton-user/looker-studio-mcp.git
cd looker-studio-mcp
# Installer les dépendances
pip install -r requirements.txt
# Installer Chromium pour Playwright
playwright install chromium
đŻ Utilisation
Mode rapide (screenshot)
python3 looker-studio-automation.py screenshot "https://lookerstudio.google.com/report/xxx" /tmp/dashboard.png
Mode interactif
python3 looker-studio-automation.py interactive
Commandes disponibles :
| Commande | Description |
|---|---|
create <titre> |
Créer un nouveau rapport |
list |
Lister mes rapports |
screenshot <path> |
Capture d'écran |
chart <type> |
Ajouter un graphique |
export |
Exporter en CSV |
open <url> |
Ouvrir une URL |
quit |
Quitter |
En tant que module Python
import asyncio
from looker_studio_automation import LookerStudioAutomation
async def main():
auto = LookerStudioAutomation(headless=False)
await auto.start()
# Ouvrir Looker Studio
await auto.open_looker_studio()
# Attendre le login manuel
input("Connecté? Appuie sur Entree...")
# Créer un rapport
await auto.create_report("Mon Dashboard")
# Ajouter un graphique
await auto.add_chart("Scorecard")
# Screenshot
await auto.take_screenshot("/tmp/dashboard.png")
await auto.stop()
asyncio.run(main())
đ Structure du projet
looker-studio-mcp/
âââ looker-studio-automation.py # Script principal
âââ requirements.txt # DĂ©pendances Python
âââ README.md # Documentation
âââ LICENSE # License MIT
âââ .gitignore # Fichiers exclus
âââ examples/ # Exemples d'utilisation
âââ example_usage.py
đ§ DĂ©pendances
playwright>=1.40.0
â ïž Pitfalls & Notes
Profil Chrome persistant
Le script utilise un profil Chrome persistant (~/.hermes/looker-studio-chrome/) pour garder la session Google entre les exécutions. Cela évite de se reconnecter à chaque fois.
Login Google
La premiÚre exécution nécessite un login manuel dans le navigateur. Ensuite, la session est sauvegardée.
Sélecteurs CSS
Google modifie rĂ©guliĂšrement les sĂ©lecteurs CSS de Looker Studio. Si le script ne fonctionne plus, il faudra peut-ĂȘtre mettre Ă jour les sĂ©lecteurs.
Headless mode
Certains éléments UI ne fonctionnent pas en mode headless. Utilisez headless=False pour les opérations complexes.
đ€ Contribuer
- Fork le projet
- Créer une branche (
git checkout -b feature/amazing-feature) - Commit (
git commit -m 'Add amazing feature') - Push (
git push origin feature/amazing-feature) - Ouvrir une Pull Request
đ License
Ce projet est sous License MIT â voir le fichier LICENSE pour plus de dĂ©tails.
đ CrĂ©dits
- Playwright â Automatisation de navigateur
- Google Looker Studio â Outil de visualisation de donnĂ©es
đ§ Contact
Jmarc â jmd@talandria.fr
Projet Link: https://github.com/ton-user/looker-studio-mcp
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.