Get a specific email by message ID
AI agents call gmail-get-email to retrieve information from Google Services MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves email content based on a message ID. It is a query operation that reads data from Gmail without side effects, reversible changes, or external execution. The blast radius is minimal: exposure would allow an attacker to read emails the authenticated account can access, but not modify, delete, send, or execute code. Classified as Read with low severity.
From the tool's definition The tool name and description indicate it 'Get[s] a specific email by message ID' — a retrieval operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Get a specific email by message ID. It is categorised as a Read tool in the Google Services MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Google Services MCP Server MCP server in PolicyLayer and add a rule for gmail-get-email: 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 Google Services MCP Server. Nothing to install.
gmail-get-email 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 gmail-get-email 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 gmail-get-email. 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.
gmail-get-email is provided by the Google Services MCP Server MCP server (ricleedo/google-service-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 →