count_gmail_messages
AI agents call count_gmail_messages to retrieve information from Google Connections without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Counting messages is a read-only operation with no side effects. It retrieves information from Gmail without creating, modifying, or deleting any data. Even if an AI agent misuses this tool, the blast radius is minimal—it can only query message counts. Confidence is high based on the clear semantic meaning of the tool name, though slightly reduced due to the empty description.
From the tool's definition Tool name 'count_gmail_messages' indicates a query operation that retrieves a count of messages. The description is empty, but the name and server context (Gmail API access) strongly suggest this returns message counts without modifying data.
Attacks that exploit this kind of access
count_gmail_messages. It is categorised as a Read tool in the Google Connections MCP Server, which means it retrieves data without modifying state.
Register the Google Connections MCP server in PolicyLayer and add a rule for count_gmail_messages: 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 Connections. Nothing to install.
count_gmail_messages 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 count_gmail_messages 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 count_gmail_messages. 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.
count_gmail_messages is provided by the Google Connections MCP server (michaelzrork/google-connections-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 →