Verify if an email address is valid and deliverable.
AI agents call hunter_verify_email to retrieve information from Hunter Io MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs email verification through an API query, which is a read operation. It retrieves information about whether an email is valid and deliverable but does not modify data, execute code, delete records, or create financial obligations.
From the tool's definition Tool description states 'Verify if an email address is valid and deliverable' — this is a query operation that checks email validity without creating, modifying, deleting, or executing actions with side effects.
Attacks that exploit this kind of access
Verify if an email address is valid and deliverable. It is categorised as a Read tool in the Hunter Io MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Hunter Io MCP Server MCP server in PolicyLayer and add a rule for hunter_verify_email: 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 Hunter Io MCP Server. Nothing to install.
hunter_verify_email 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 hunter_verify_email 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 hunter_verify_email. 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.
hunter_verify_email is provided by the Hunter Io MCP Server MCP server (meerkats-ai/hunter-io-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 →