// SCAN REPORT

M365connector

5 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated: 5 Jul 2026

0 can modify or destroy data

5 read-only

5 tools total

Community server · catalogue entry verified 05/07/2026

How to control M365connector ↓

TOOL MAP

What M365connector exposes to your agents

Read (5) Write / Execute (0) Destructive / Financial (0)

Running more than one server? Check your whole stack →

THE RISK

What can go wrong

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

POLICY

How to control M365connector

PolicyLayer is an MCP gateway — it sits between your AI agents and M365connector, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "count_people": {
    "limits": [
      {
        "counter": "count_people_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register M365connector — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON M365CONNECTOR →

Instant setup, no code required.

FULL CATALOGUE

All 5 M365connector tools

READ 5 tools

Read count_people Count people matching filters in Microsoft Graph directory data. Returns only the count, not the full results. Read find_people Find people from Microsoft Graph directory data using query, alias, principal name, display name, department, Read open Open and read content for a prior search result. Returns a summary with metadata. Small content is returned in Read search Search across Microsoft 365 data including emails, files, Teams chats, calendar events, and external connector Read whoami Get the current signed-in user

FAQ

Questions about M365connector

Is the M365connector MCP server safe to use without restrictions? +

The M365connector server is primarily read-only with 5 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the M365connector MCP server expose? +

5 tools across 2 categories: Read, Write. 5 are read-only. 0 can modify, create, or delete data.

How do I enforce a policy on M365connector? +

Register the M365connector MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every M365connector tool call.

Deterministic rules across all 5 M365connector tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON M365CONNECTOR →

Instant setup, no code required.

5 M365connector tools catalogued and risk-classified — across an index of 43,000+ MCP servers.