AI agents invoke m365_chat_with_files to trigger actions in M365 Copilot. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The description is empty, so classification relies on the tool name and server context. 'Chat with files' suggests an interactive query/execution operation against M365 files, likely invoking the Copilot API to process file contents. Given sibling tools like m365_retrieve and m365_search exist for read operations, this tool likely executes a conversational AI interaction over files, placing it in Execute.
From the tool's definition Tool name 'm365_chat_with_files' and empty description; server context involves M365 data including SharePoint, OneDrive, emails, calendars, and Teams
Documented attack patterns abuse exactly the kind of access m365_chat_with_files 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_chat_with_files:
{
"version": "1",
"default": "deny",
"tools": {
"m365_chat_with_files": {
"limits": [
{
"counter": "m365_chat_with_files_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}m365_chat_with_files stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
m365_chat_with_files. It is categorised as a Execute tool in the M365 Copilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the M365 Copilot MCP server in PolicyLayer and add a rule for m365_chat_with_files: 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_chat_with_files is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the m365_chat_with_files 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_chat_with_files. 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_chat_with_files 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.