AI agents call contacts_search_all to retrieve information from Google without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves contact data from personal contacts and directory without creating, modifying, deleting, or executing any operations. It is purely informational/retrieval in nature, making it a Read category tool with low severity since contact search has minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'contacts_search_all' and description 'Search both personal contacts and directory (comprehensive search)' indicate a query operation with no modification or side effects.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Search both personal contacts and directory (comprehensive search). It is categorised as a Read tool in the Google MCP Server, which means it retrieves data without modifying state.
Register the Google MCP server in PolicyLayer and add a rule for contacts_search_all: 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. Nothing to install.
contacts_search_all 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 contacts_search_all 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 contacts_search_all. 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.
contacts_search_all is provided by the Google MCP server (robcerda/google-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 →