Microsoft 365 MCP Server

What does “Microsoft 365” MCP Server do?

The Microsoft 365 MCP Server is a Model Context Protocol (MCP) server designed to facilitate seamless interaction between AI assistants and Microsoft 365 services via the Graph API. By serving as a bridge between language models and the Microsoft 365 ecosystem, this server empowers AI-driven workflows with capabilities such as querying emails, managing calendar events, handling files within OneDrive, and interacting with tasks and contacts. Developers can leverage this server to automate and streamline activities like document management, scheduling, and communications, directly from their AI tools. This integration significantly enhances productivity by allowing LLMs to execute complex operations across the Microsoft 365 suite, making it ideal for enterprise environments seeking to connect their AI solutions with real-world data and services.

List of Prompts

No information available in the repository regarding prompt templates.

List of Resources

No information available in the repository regarding MCP resources.

List of Tools

No explicit list of tools found in server.py or the repository structure. However, based on the README features, probable tools include:

• Excel file operations: For reading and writing Excel files in Microsoft 365.
• Calendar event management: For creating, updating, or deleting calendar events.
• Mail operations: To send, receive, and organize emails within Outlook.
• OneDrive file management: To upload, download, or manage files in OneDrive.
• OneNote notebooks and pages: For manipulating notes and pages in OneNote.
• To Do tasks and task lists: For managing tasks and task lists in Microsoft To Do.
• Planner plans and tasks: To interact with Planner plans and tasks.
• Outlook contacts: For managing contact information within Outlook.

Use Cases of this MCP Server

• Document Automation: Automate reading, writing, and organizing Excel and OneDrive documents, streamlining reporting and file management tasks for organizations.
• Calendar Scheduling: Enable AI assistants to create, update, or delete calendar events, helping users manage appointments and meetings more efficiently.
• Email Management: Allow LLMs to send, categorize, or retrieve emails, improving workflow automation and communications within enterprise contexts.
• Task Tracking: Facilitate the management of tasks across Microsoft To Do and Planner, helping teams and individuals stay organized and productive.
• Contact Management: Automate the organization and updating of Outlook contacts, making it easier to maintain up-to-date communication lists.

How to set it up

Windsurf

1. Ensure Node.js >= 14 is installed.
2. Open your Windsurf configuration file.
3. Add the Microsoft 365 MCP Server using the following JSON snippet:

   {
     "mcpServers": {
       "ms-365-mcp": {
         "command": "npx",
         "args": ["@softeria/ms-365-mcp-server@latest"]
       }
     }
   }
   

4. Save the configuration and restart Windsurf.
5. Verify that the MCP server is running and accessible.

Securing API Keys: Store sensitive credentials in environment variables. Example:

{
  "env": {
    "MS_CLIENT_ID": "your-client-id",
    "MS_CLIENT_SECRET": "your-client-secret"
  },
  "inputs": {
    "tenantId": "your-tenant-id"
  }
}

Claude

1. Install Node.js >= 14.
2. Access Claude’s settings or configuration file.
3. Integrate the Microsoft 365 MCP Server as follows:

   {
     "mcpServers": {
       "ms-365-mcp": {
         "command": "npx",
         "args": ["@softeria/ms-365-mcp-server@latest"]
       }
     }
   }
   

4. Save changes and restart Claude.
5. Confirm that the server is recognized by Claude.

Securing API Keys:
Use environment variables just like the example above.

Cursor

1. Make sure Node.js >= 14 is available.
2. Locate Cursor’s MCP configuration file.
3. Add the MCP server:

   {
     "mcpServers": {
       "ms-365-mcp": {
         "command": "npx",
         "args": ["@softeria/ms-365-mcp-server@latest"]
       }
     }
   }
   

4. Save and restart the Cursor environment.
5. Test the connection to Microsoft 365 MCP.

Securing API Keys:
Refer to the environment variable structure shown above.

Cline

1. Install Node.js >= 14.
2. Access Cline’s configuration file for MCP servers.
3. Register the Microsoft 365 MCP Server:

   {
     "mcpServers": {
       "ms-365-mcp": {
         "command": "npx",
         "args": ["@softeria/ms-365-mcp-server@latest"]
       }
     }
   }
   

4. Save and restart Cline.
5. Check server connectivity and operation.

Securing API Keys:
Set your credentials as environment variables as previously shown.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "ms-365-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “ms-365-mcp” to whatever the actual name of your MCP server is and replace the URL with your MCP server URL.

Overview

Based on the available documentation, this MCP server covers the basics of Microsoft 365 integration and provides setup instructions, but lacks explicit prompt/resource/tool details in MCP format and doesn’t mention Roots or sampling support. I would rate this MCP server a 6/10 for completeness and clarity.

MCP Score