nitin27may/ms-graph-mcp
by Various
Microsoft Graph MCP server for AI agents — 85 tools across Outlook mail & calendar, Teams, OneDrive, SharePoint, OneNote, Planner and Entra ID. Delegated OAuth, stdio or Streamable
MCP
nitin27may/ms-graph-mcp
Added 21 Sept 2026
Overview
Microsoft Graph MCP server for AI agents. Exposes 85 tools covering Outlook mail and calendar, Teams, OneDrive, SharePoint, OneNote, Planner, and Entra ID. Uses delegated OAuth and supports stdio or Streamable HTTP transport.
Best for
Best for
Developers building AI agents that need read/write access to Microsoft 365 data via MCP.
Use cases
- Automate email and calendar workflows through AI agents
- Query and manage Teams, OneDrive, and SharePoint files
- Access Planner tasks and Entra ID directory data via MCP
How to use
Install
npx @modelcontextprotocol/inspector \ Tools exposed
GRAPH_MCP_CLIENT_IDGRAPH_MCP_TENANT_IDGRAPH_MCP_SCOPESGRAPH_MCP_TOOLSETSGRAPH_MCP_WRITE_SCOPEGRAPH_MCP_READ_ONLYGRAPH_MCP_LOG_LEVEL
Tested with
Claude Desktop, Claude Code, Cursor, Windsurf, VS Code
Notes
Microsoft Graph MCP server for AI agents. Exposes 85 tools covering Outlook mail and calendar, Teams, OneDrive, SharePoint, OneNote, Planner, and Entra ID. Uses delegated OAuth and supports stdio or Streamable HTTP transport.
3 stars on GitHub. Last updated 2026-09-18. Licensed MIT.
Use cases
- Automate email and calendar workflows through AI agents
- Query and manage Teams, OneDrive, and SharePoint files
- Access Planner tasks and Entra ID directory data via MCP
Pros
- Broad tool coverage across Microsoft 365 services
- Supports both stdio and Streamable HTTP for flexible deployment
- Uses delegated OAuth for user-scoped access
Cons
- Only 3 GitHub stars, indicating minimal adoption
- Requires Python environment and OAuth configuration
- No official vendor backing (vendor listed as Various)
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Broad tool coverage across Microsoft 365 services
- Supports both stdio and Streamable HTTP for flexible deployment
- Uses delegated OAuth for user-scoped access
Cons
- Only 3 GitHub stars, indicating minimal adoption
- Requires Python environment and OAuth configuration
- No official vendor backing (vendor listed as Various)
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
