MCP Server Microsoft365 Filesearch

🚀 MCP Server - Microsoft 365 File Search (SharePoint and OneDrive)

An MCP server implementation that provides advanced file search capabilities in the Microsoft 365 environment, enabling efficient file discovery, metadata analysis, and integration with business processes by offering content from SharePoint and OneDrive.

🚀 Quick Start

This MCP server offers advanced file search functionality within the Microsoft 365 environment. It comes with useful tools and caching mechanisms to enhance performance. You can also integrate it with Claude Desktop and use it after registering an app in the Azure portal.

✨ Features

• Advanced Search: Conduct high - level file searches in the Microsoft 365 environment.
• Efficient Tools: Provide two core tools for file search and content retrieval.
• Local Caching: Store downloaded files locally to improve performance and reduce redundant API calls.
• Claude Desktop Integration: Seamlessly integrate with Claude Desktop.

📦 Installation

Prerequisites

• Register an application in the Azure portal and obtain the CLIENT_ID, CLIENT_SECRET, and TENANT_ID.
• Configure the claude_desktop_config.json file correctly.

💻 Usage Examples

Integrating with Claude Desktop

Update the claude_desktop_config.json as follows:

"mcpServers": {
  "M365 File Search (SharePoint/OneDrive)": {
    "command": "uv",
    "args": [
      "--directory",
      "full_path_to_parent_directory",
      "run",
      ".\\src\\mcp_m365_filesearch\\server.py"
    ],
    "env": {
      "CLIENT_ID": "MSGraph 客户端 ID",
      "CLIENT_SECRET": "MS Graph 客户端密钥",
      "TENANT_ID": "租户 ID",
      "REGION": "搜索区域"
    }
  }
}

Using the Core Tools

Basic Usage

# Example of using search_m365_files
from your_module import search_m365_files
query = "example_query"
result = search_m365_files(query)
print(result)

# Example of using get_file_content
from your_module import get_file_content
driveid = "example_driveid"
fileid = "example_fileid"
content = get_file_content(driveid, fileid)
print(content)

📚 Documentation

Components

Tools

The server provides two core tools:

• search_m365_files
  Execute file searches in the Microsoft 365 environment.
  Input:

  • query (string): Search term or condition.
    Return: An array of file metadata objects. Metadata includes details such as file content summaries, Drive ID, and File ID.

• get_file_content
  Retrieve the content of a specific file.
  Input:

  • driveid (string): The unique identifier of the parent drive.
  • fileid (string): The unique identifier of the file.
    Return: The file content as a binary stream.
    Note: Use local caching to speed up repeated access.

Cache

To improve performance and reduce redundant API calls, the server caches downloaded files locally.

• Cached files are stored in the ./src/mcp_m365_filesearch/.local/downloads directory (relative path) under the project root.
• When requesting a file via get_file_content, the server first checks the cache.
• If the file is cached, it is returned directly from disk without a new API call.

Microsoft Graph Application Registration

To use this server, you need to register an application in the Azure portal:

1. Register a new application.
2. Record the CLIENT ID and TENANT ID.
3. Create a CLIENT SECRET under Certificates & secrets.
4. Under API permissions, add the following Delegated or Application permissions:
   • Sites.Read.All
   • Files.Read.All
5. Click Grant admin consent for these permissions.

📄 License

This project is released under the MIT License. You are free to use, modify, and distribute the project, provided that appropriate attribution is given.