m365-copilot-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AZURE_CLIENT_ID | Yes | App registration client ID from the Azure Portal. | |
| AZURE_TENANT_ID | Yes | Azure AD tenant ID from the Azure Portal. | |
| PYTHONUNBUFFERED | No | Used to ensure output is sent immediately to the terminal or logs. | |
| AZURE_CLIENT_SECRET | No | Only required for confidential clients. | |
| M365_COPILOT_TIMEOUT | No | Request timeout in seconds (default: 60). | 60 |
| M365_COPILOT_CACHE_DIR | No | Token cache location. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| m365_retrieveA | Retrieve raw text chunks from M365 for YOUR AI to reason over. |
| m365_chatA | Quick Q&A with M365 Copilot. |
| m365_meetingsA | Get AI-generated meeting summaries, action items, and mentions from Teams. |
| m365_searchA | Find documents in OneDrive using semantic + keyword hybrid search. |
| m365_chat_with_filesA | Ask questions about specific documents you already have URIs for. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose with minimal overlap. m365_chat is for quick Q&A, m365_chat_with_files is for analyzing specific documents, m365_meetings is for meeting insights, m365_retrieve is for raw text retrieval, and m365_search is for document discovery. The descriptions explicitly differentiate use cases and when to use one tool over another, preventing confusion.
All tool names follow a consistent 'm365_' prefix with descriptive suffixes (chat, chat_with_files, meetings, retrieve, search). This pattern is uniform across all tools, making them easily identifiable and predictable, with no deviations in style or structure.
With 5 tools, the server is well-scoped for interacting with Microsoft 365 Copilot. Each tool serves a specific function (e.g., chat, file analysis, meeting summaries, retrieval, search), covering key workflows without being overly broad or sparse, making the count appropriate for the domain.
The tool set covers major M365 Copilot interactions: Q&A, document analysis, meeting insights, raw retrieval, and search. Minor gaps include limited SharePoint support in m365_search (noted as 'coming') and no explicit tools for calendar/email management beyond chat, but agents can work around these with the provided tools for core workflows.