Fire in da houseTop Tip:Most people pay up to $340 per month for Perplexity, MidJourney, Runway, ChatGPT, and more - but you can get them all your AI tools for $15 with Galaxy. It's free to test!Fire in da houseCheck it out

sharepoint-mcp

MCP.Pizza Chef: DEmodoriGatsuO

SharePoint MCP server enables LLM applications to access and query SharePoint site content through Microsoft Graph API. It allows browsing document libraries, retrieving list data, and interacting with SharePoint content using natural language, facilitating seamless integration of SharePoint data into AI workflows. This server is compatible with MCP and supports Python 3.10+ environments.

Use This MCP server To

Query SharePoint documents using natural language Browse SharePoint document libraries from LLMs Retrieve SharePoint list data for AI processing Integrate SharePoint content into AI workflows Enable LLMs to access Microsoft Graph API data Automate SharePoint data extraction for reports Use LLMs to summarize SharePoint documents Search SharePoint lists with conversational queries

README

License: MIT Python 3.10+ MCP

SharePoint MCP Server

DISCLAIMER: This project is not affiliated with, endorsed by, or related to Microsoft Corporation. SharePoint and Microsoft Graph API are trademarks of Microsoft Corporation. This is an independent, community-driven project.

SharePoint Model Context Protocol (MCP) server acts as a bridge that enables LLM applications (like Claude) to access content from your SharePoint site. With this project, you can use natural language to query documents, lists, and other content in your SharePoint site.

Features

  • Browse Document Libraries: View contents of SharePoint document libraries
  • Access List Data: Retrieve and manipulate SharePoint list data
  • Retrieve Document Content: Access content from specific documents
  • SharePoint Search: Search across your entire site
  • Create List Items: Add new items to SharePoint lists

Prerequisites

  • Python 3.10 or higher
  • Access to a SharePoint site
  • Microsoft Azure AD application registration (for authentication)

Quickstart

Follow these steps to get the SharePoint MCP Server up and running quickly:

  1. Prerequisites

    • Ensure you have Python 3.10+ installed
    • An Azure AD application with proper permissions (see docs/auth_guide.md)
  2. Installation

    # Install from GitHub
    pip install git+https://github.com/DEmodoriGatsuO/sharepoint-mcp.git
    
    # Or install in development mode
    git clone https://github.com/DEmodoriGatsuO/sharepoint-mcp.git
    cd sharepoint-mcp
    pip install -e .
  3. Configuration

    # Copy the example configuration
    cp .env.example .env
    
    # Edit the .env file with your details
    nano .env
  4. Run the Diagnostic Tools

    # Check your configuration
    python config_checker.py
    
    # Test authentication
    python auth-diagnostic.py
  5. Start the Server

    python server.py

Installation

  1. Clone the repository:
git clone https://github.com/DEmodoriGatsuO/sharepoint-mcp.git
cd sharepoint-mcp
  1. Create and activate a virtual environment:
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
  1. Install dependencies:
pip install -r requirements.txt
  1. Set up environment variables:
cp .env.example .env
# Edit the .env file with your authentication details

Configuration

  1. Register an application in Azure AD and grant necessary permissions (see docs/auth_guide.md)
  2. Configure your authentication information and SharePoint site URL in the .env file

Usage

Run in Development Mode

mcp dev server.py

Install in Claude Desktop

mcp install server.py --name "SharePoint Assistant"

Run Directly

python server.py

Advanced Usage

Handling Document Content

# Example of retrieving document content
import requests

# Get document content
response = requests.get(
    "http://localhost:8080/sharepoint-mcp/document/Shared%20Documents/report.docx", 
    headers={"X-MCP-Auth": "your_auth_token"}
)

# Process content
if response.status_code == 200:
    document_content = response.json()
    print(f"Document name: {document_content['name']}")
    print(f"Size: {document_content['size']} bytes")

Working with SharePoint Lists

# Example of retrieving list data
import requests
import json

# Get list items
response = requests.get(
    "http://localhost:8080/sharepoint-mcp/list/Tasks", 
    headers={"X-MCP-Auth": "your_auth_token"}
)

# Create a new list item
new_item = {
    "Title": "Review quarterly report",
    "Status": "Not Started",
    "DueDate": "2025-05-01"
}

create_response = requests.post(
    "http://localhost:8080/sharepoint-mcp/list/Tasks", 
    headers={
        "X-MCP-Auth": "your_auth_token",
        "Content-Type": "application/json"
    },
    data=json.dumps(new_item)
)

Integrating with Claude

See the documentation in docs/usage.md for detailed examples of how to use this server with Claude and other LLM applications.

Monitoring and Troubleshooting

Logs

The server logs to stdout by default. Set DEBUG=True in your .env file to enable verbose logging.

Common Issues

  • Authentication Failures: Run python auth-diagnostic.py to diagnose issues
  • Permission Errors: Make sure your Azure AD app has the required permissions
  • Token Issues: Use python token-decoder.py to analyze your token's claims

License

This project is released under the MIT License. See the LICENSE file for details.

Contributing

Contributions are welcome. Please open an issue first to discuss what you would like to change before making major modifications. See CONTRIBUTING.md for guidelines.

sharepoint-mcp FAQ

How do I authenticate the SharePoint MCP server?
Authentication is done via Microsoft Graph API credentials, typically using OAuth tokens configured in the server settings.
Can this server access both documents and lists in SharePoint?
Yes, it supports browsing document libraries and retrieving list data from SharePoint sites.
Is the SharePoint MCP server compatible with multiple LLM providers?
Yes, it works with any MCP-compatible LLMs including OpenAI, Anthropic Claude, and Google Gemini.
What programming languages are supported for running this server?
The server is implemented in Python 3.10+, ensuring compatibility with modern Python environments.
Does this server require a Microsoft 365 subscription?
Yes, access to SharePoint content via Microsoft Graph API requires appropriate Microsoft 365 licenses.
How secure is the data accessed through this MCP server?
Security depends on Microsoft Graph API permissions and OAuth scopes configured; the server does not store data persistently.
Can I customize which SharePoint sites or libraries the server accesses?
Yes, configuration allows specifying target SharePoint sites and document libraries for access.
Is this project officially supported by Microsoft?
No, this is an independent community-driven project not affiliated with Microsoft Corporation.