AI agents call m365_retrieve 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.
The name 'm365_retrieve' strongly suggests fetching or retrieving data from Microsoft 365 services without modification. However, confidence is reduced to 0.75 because the description is empty and cannot confirm the exact scope or constraints.
From the tool's definition Tool name 'm365_retrieve' indicates a retrieval operation, typical of Read category tools. Server context shows integration with Microsoft 365 data sources (SharePoint, OneDrive, emails, calendars, Teams) with 'enterprise permission enforcement.' Sibling…
Documented attack patterns abuse exactly the kind of access m365_retrieve gives an agent:
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_retrieve:
{
"version": "1",
"default": "deny",
"tools": {
"m365_retrieve": {}
}
}m365_retrieve is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
m365_retrieve. It is categorised as a Read tool in the M365 Copilot MCP Server, which means it retrieves data without modifying state.
Register the M365 Copilot MCP server in PolicyLayer and add a rule for m365_retrieve: 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.
m365_retrieve is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the m365_retrieve 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.
Set action: deny in the PolicyLayer policy for m365_retrieve. 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.
m365_retrieve 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.
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.