AI agents call emailrules_get to retrieve information from M365 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Email rules are configuration data that control how incoming messages are processed. A 'get' operation retrieves this information for viewing or analysis purposes. Since the description is empty, confidence is slightly reduced, but the naming convention and context of the M365 email management server strongly suggest this is a read-only retrieval of email rule settings, consistent with querying data about filter…
From the tool's definition Tool name 'emailrules_get' indicates retrieval of email rules configuration. The suffix '_get' is characteristic of read operations that query existing data without modification.
Attacks that exploit this kind of access
emailrules_get. It is categorised as a Read tool in the M365 MCP Server, which means it retrieves data without modifying state.
Register the M365 MCP server in PolicyLayer and add a rule for emailrules_get: 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.
emailrules_get 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 emailrules_get 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 emailrules_get. 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.
emailrules_get 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →