Dry-run archive candidates grouped by account and reason with message ids and subjects.
AI agents call mail_archive_plan to retrieve information from Personal Mail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool is explicitly described as a 'dry-run', meaning it only simulates and reports what would be archived without actually performing any archival action. It retrieves and groups candidate messages by account and reason, making it a read/query operation with no side effects.
From the tool's definition Dry-run archive candidates grouped by account and reason with message ids and subjects.
Attacks that exploit this kind of access
Dry-run archive candidates grouped by account and reason with message ids and subjects. It is categorised as a Read tool in the Personal Mail MCP Server, which means it retrieves data without modifying state.
Register the Personal Mail MCP server in PolicyLayer and add a rule for mail_archive_plan: 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 Personal Mail. Nothing to install.
mail_archive_plan 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 mail_archive_plan 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 mail_archive_plan. 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.
mail_archive_plan is provided by the Personal Mail MCP server (srogerf/personal-mail-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 →