Searches gmail inbox using a search query query.
AI agents call search_gmail_emails to retrieve information from Enterprise AI Bridge (MCP) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries and retrieves email messages. However, severity is elevated to 'medium' rather than 'low' because email often contains sensitive personal information (credentials, financial details, confidential communications, PII). While the tool itself performs no side effects, misuse by an AI agent could expose sensitive data.
From the tool's definition Tool name 'search_gmail_emails' and description 'Searches gmail inbox using a search query' indicate retrieval of email data with no modification or deletion.
Attacks that exploit this kind of access
Searches gmail inbox using a search query query. It is categorised as a Read tool in the Enterprise AI Bridge (MCP) MCP Server, which means it retrieves data without modifying state.
Register the Enterprise AI Bridge (MCP) MCP server in PolicyLayer and add a rule for search_gmail_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 Enterprise AI Bridge (MCP). Nothing to install.
search_gmail_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_gmail_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_gmail_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_gmail_emails is provided by the Enterprise AI Bridge (MCP) MCP server (olegvasilievcs/mcp-server). 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 →