AI agents use email_add_category 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.
This tool creates or modifies email attributes (categories/labels) reversibly. It does not delete data (would be Destructive), execute code (would be Execute), or move money (would be Financial). The severity is medium because misuse could result in organizational emails being miscategorized, impacting workflow and information retrieval, but the action is reversible.
From the tool's definition Tool name 'email_add_category' indicates modifying email metadata by adding a category/label to an email message. The description is empty, limiting direct verification, but the naming pattern aligns with write operations on email data.
Attacks that exploit this kind of access
email_add_category. 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 email_add_category: 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.
email_add_category 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 email_add_category 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 email_add_category. 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.
email_add_category 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 →