AI agents use cache_invalidate to create or update resources in M365 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your M365 environment.
The tool modifies system state by invalidating cached data, which is reversible and non-destructive—new cache entries can be regenerated. This matches Write category (modifies data reversibly) rather than Destructive.
From the tool's definition Tool name 'cache_invalidate' indicates modification of cached data state; it invalidates/clears cache entries, which is a reversible data modification operation (cache can be rebuilt/rewarmed, as evidenced by sibling 'cache_warming_status' tool).
Attacks that exploit this kind of access
cache_invalidate. It is categorised as a Write tool in the M365 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the M365 MCP server in PolicyLayer and add a rule for cache_invalidate: 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. Nothing to install.
cache_invalidate is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cache_invalidate 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 cache_invalidate. 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.
cache_invalidate is provided by the M365 MCP server (robin-collins/m365-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
cache_invalidate is one line of M365's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →