Search contacts by name/email/phone/company substring (Google People searchContacts).
AI agents call find_contact to retrieve information from Nexus Core 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 based on search criteria but does not create, modify, delete, or execute any actions. It is a pure data retrieval operation with no side effects. Severity is low because contact search results present minimal risk even if returned to an untrusted agent - they contain only contact metadata that is typically not sensitive financial or destructive in nature.
From the tool's definition Tool description states it "Search contacts by name/email/phone/company substring" - a query operation with no modification, deletion, or execution capability. Uses Google People API searchContacts which is a read-only search function.
Attacks that exploit this kind of access
Search contacts by name/email/phone/company substring (Google People searchContacts). It is categorised as a Read tool in the Nexus Core MCP Server, which means it retrieves data without modifying state.
Register the Nexus Core MCP server in PolicyLayer and add a rule for find_contact: 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 Nexus Core. Nothing to install.
find_contact 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 find_contact 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 find_contact. 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.
find_contact is provided by the Nexus Core MCP server (noumenon-ai/nexus-core). 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 →