Low Risk

m365_search

m365_search

How to control m365_search ↓

What m365_search does on M365 Copilot

AI agents call m365_search to retrieve information from M365 Copilot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why m365_search needs a policy

Although the description is empty (lowering confidence slightly), the tool name 'search' and its context within an M365 integration server that 'enables natural language queries' clearly indicates this is a Read operation—it retrieves data from enterprise systems.

From the tool's definition Tool name 'm365_search' combined with server context indicating it integrates Microsoft 365 data (SharePoint, OneDrive, emails, calendars, Teams) and sibling tool 'm365_retrieve' suggest query/search operations.

Documented attack patterns abuse exactly the kind of access m365_search gives an agent:

How to control m365_search

PolicyLayer is an MCP gateway — it sits between your AI agents and M365 Copilot, and nothing reaches the server without passing your rules. This is the rule we recommend for m365_search:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "m365_search": {}
  }
}

m365_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register M365 Copilot — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about m365_search

What does the m365_search tool do? +

m365_search. It is categorised as a Read tool in the M365 Copilot MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on m365_search? +

Register the M365 Copilot MCP server in PolicyLayer and add a rule for m365_search: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches M365 Copilot. Nothing to install.

What risk level is m365_search? +

m365_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit m365_search? +

Yes. Add a rate_limit block to the m365_search rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block m365_search completely? +

Set action: deny in the PolicyLayer policy for m365_search. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides m365_search? +

m365_search is provided by the M365 Copilot MCP server (renepajta/m365-copilot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every M365 Copilot tool call.

Start from M365 Copilot, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

5 M365 Copilot tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.