AI agents call contacts_search to retrieve information from Access without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves contact information from Google Contacts without creating, modifying, or deleting data. It is a query/search operation that reads personal contact data. While contact information can be sensitive, the severity is low because the tool cannot modify data, execute actions, or cause irreversible harm.
From the tool's definition Tool description states it 'Search[es] Google Contacts by name, email address, or phone number' and 'Returns matching contacts'. The verb 'search' and 'returns' indicate data retrieval with no modification. No side effects mentioned.
Attacks that exploit this kind of access
Search Google Contacts by name, email address, or phone number. Returns matching contacts with their full names, emails, phone numbers, and organizations. It is categorised as a Read tool in the Access MCP Server, which means it retrieves data without modifying state.
Register the Access MCP server in PolicyLayer and add a rule for contacts_search: 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 Access. Nothing to install.
contacts_search 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 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. 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 is provided by the Access MCP server (scottpedia0/access). 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 →