mail_get
AI agents call mail_get to retrieve information from Hermes Google without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite empty description, the semantic pattern 'mail_get' combined with the server's purpose (managing Gmail/Calendar/Drive) and comparison with similar sibling tools strongly indicates this retrieves or queries email data without side effects. Confidence is reduced by 0.15 due to missing explicit description, but the name alone provides sufficient evidence for Read classification.
From the tool's definition Tool name 'mail_get' suggests retrieval of email messages. Sibling tools include 'mail_*' operations alongside 'drive_get' (explicitly Read category) and destructive counterparts like 'drive_delete', 'cal_delete_event'.
Attacks that exploit this kind of access
mail_get. It is categorised as a Read tool in the Hermes Google MCP Server, which means it retrieves data without modifying state.
Register the Hermes Google MCP server in PolicyLayer and add a rule for mail_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 Hermes Google. Nothing to install.
mail_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 mail_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 mail_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.
mail_get is provided by the Hermes Google MCP server (jimmy-larsson/hermes-google). 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 →