AVOCarbon SharePoint MCP
Enables managing SharePoint and OneDrive files, folders, permissions, and versions through Microsoft Graph API with actions like upload, download, search, and sharing.
README
AVOCarbon SharePoint MCP
Serveur MCP Python pour gérer SharePoint et OneDrive avec Microsoft Graph.
Actions incluses
- Profil, sites et bibliothèques
- Navigation dans les dossiers
- Recherche et lecture de fichiers
- Création de dossiers
- Upload simple et upload par blocs
- Mise à jour, copie, déplacement, renommage et suppression
- Liens de partage, invitations et permissions
- Liste et restauration des versions
Configuration
Copier le modèle :
cp .env.example .env
Renseigner un nouveau secret Azure :
AZURE_TENANT_ID=4e99b5ff-dd77-418a-8b69-1d684e911168
AZURE_CLIENT_ID=653f4fbf-ba11-406c-98ea-e61d637d79d0
AZURE_CLIENT_SECRET=your-new-secret
Le fichier .env est exclu de Git par .gitignore.
Permissions Microsoft Graph
Pour un premier test avec des permissions d'application :
Sites.ReadWrite.AllFiles.ReadWrite.All
Accorder ensuite le consentement administrateur. Pour la production, préférer Sites.Selected afin de limiter l'accès aux sites requis.
Démarrage local
python -m venv .venv
# Windows
.venv\Scripts\activate
# Linux/macOS
source .venv/bin/activate
pip install -r requirements.txt
python server.py
Endpoint MCP :
http://localhost:8000/mcp
Docker
docker build -t avocarbon-sharepoint-mcp .
docker run --rm -p 8000:8000 --env-file .env avocarbon-sharepoint-mcp
Azure App Service
Ajouter les paramètres d'application suivants :
AZURE_TENANT_ID
AZURE_CLIENT_ID
AZURE_CLIENT_SECRET
HOST=0.0.0.0
PORT=8000
MCP_TRANSPORT=streamable-http
Commande de démarrage :
python server.py
URL publique habituelle :
https://YOUR-APP.azurewebsites.net/mcp
Exemple AVOCarbon SharePoint
Pour https://avocarbongroup.sharepoint.com/sites/pdc/... :
get_site(hostname="avocarbongroup.sharepoint.com", site_path="/sites/pdc")list_site_drives(site_id=...)list_folder_items(drive_id=..., folder_path=...)upload_file(drive_id=..., parent_item_id=..., file_name=..., content_base64=...)
Sécurité
Ne jamais mettre un client secret réel dans GitHub, même dans un dépôt privé. Utiliser les variables d'environnement Azure App Service ou GitHub Actions Secrets.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.