// SCAN REPORT

Ms 365

9 tools. 4 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 26 Jun 2026

4 can modify or destroy data

5 read-only

9 tools total

Community server · catalogue entry verified 26/06/2026

How to control Ms 365 ↓

TOOL MAP

What Ms 365 exposes to your agents

Read (5) Write / Execute (3) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Ms 365 tools

Destructive · High remove-account Removing an account from the cache is a destructive operation that cannot be easily undone and eliminates access to that account's stored credentials/sessions. Execute · High execute-tool This tool permits execution of arbitrary Microsoft Graph API calls, which can perform a wide range of operations (read, write, delete, etc.) depending on what the caller specifies. Write · Medium select-account This tool performs a state-changing operation that affects subsequent tool behavior by designating which Microsoft account context will be used for future operations. Write · Medium login Authenticate with Microsoft account

4 of Ms 365's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ms 365

PolicyLayer is an MCP gateway — it sits between your AI agents and Ms 365, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "remove-account": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "login": {
    "limits": [
      {
        "counter": "login_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get-tool-schema": {
    "limits": [
      {
        "counter": "get-tool-schema_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 Ms 365 — 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 MS 365 →

Instant setup, no code required.

FULL CATALOGUE

All 9 Ms 365 tools

DESTRUCTIVE 1 tools

Destructive remove-account Remove a Microsoft account from the cache. Accepts email address (e.g. user@outlook.com) or account ID. Use li

EXECUTE 1 tools

Execute execute-tool Execute a Microsoft Graph API tool by name. Workflow: search-tools → get-tool-schema → execute-tool. Call get-

WRITE 2 tools

Write select-account Select a Microsoft account as the default. Accepts email address (e.g. user@outlook.com) or account ID. Use li

READ 5 tools

Read get-tool-schema Returns the full parameter schema (name, placement, required, JSON Schema) for a tool discovered via search-to Read list-accounts List all Microsoft accounts configured in this server. Use this to discover available account emails before ma Read logout Log out from Microsoft account Read search-tools Search through ${totalCount} tools (${toolsRegistry.size} Microsoft Graph API operations + ${utilityTools.leng

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Ms 365

Can an AI agent delete data through the Ms 365 MCP server? +

Yes. The Ms 365 server exposes 1 destructive tools including remove-account. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Ms 365? +

The Ms 365 server has 2 write tools including login, select-account. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Ms 365.

How many tools does the Ms 365 MCP server expose? +

9 tools across 4 categories: Destructive, Execute, Read, Write. 5 are read-only. 4 can modify, create, or delete data.

How do I enforce a policy on Ms 365? +

Register the Ms 365 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 Ms 365 tool call.

Deterministic rules across all 9 Ms 365 tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MS 365 →

Instant setup, no code required.

9 Ms 365 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.