Find a phone number using LinkedIn profile URL.
AI agents call hatch_find_phone to retrieve information from Hatch MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries phone number data from external sources (Hatch API integration), which is the hallmark of a Read category tool. However, severity is elevated from 'low' to 'medium' because phone numbers are sensitive personally identifiable information (PII); misuse by an AI agent could enable harassment, spam, or social engineering attacks.
From the tool's definition Tool description states it "Find[s] a phone number" - a retrieval operation with no modification or deletion. The input is a LinkedIn profile URL and the output is contact information. No side effects or state changes occur.
Attacks that exploit this kind of access
Find a phone number using LinkedIn profile URL. It is categorised as a Read tool in the Hatch MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hatch MCP Server MCP server in PolicyLayer and add a rule for hatch_find_phone: 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 Hatch MCP Server. Nothing to install.
hatch_find_phone 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 hatch_find_phone 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 hatch_find_phone. 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.
hatch_find_phone is provided by the Hatch MCP Server MCP server (meerkats-ai/hatch-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 →