search_emails
AI agents call search_emails to retrieve information from Claude Gmail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
search_emails retrieves and queries email data without creating, modifying, or deleting messages. This is a Read operation. Severity is medium rather than low because email often contains sensitive personal and business information; unauthorized search access could expose PII, credentials, or confidential communications.
From the tool's definition Tool name 'search_emails' and sibling tools include 'read_email' and 'send_email', establishing this server's email access pattern. The tool enables searching through emails, which is a retrieval operation with no modification capability.
Attacks that exploit this kind of access
search_emails. It is categorised as a Read tool in the Claude Gmail MCP Server, which means it retrieves data without modifying state.
Register the Claude Gmail MCP server in PolicyLayer and add a rule for search_emails: 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 Claude Gmail. Nothing to install.
search_emails 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 search_emails 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 search_emails. 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.
search_emails is provided by the Claude Gmail MCP server (pliablepixels/claude-gmail-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 →