Verify multiple email addresses in batch (max 25). Returns status and score for each.
AI agents call verify_emails_batch to retrieve information from Prospector MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the status of email addresses via DNS/SMTP verification without creating, modifying, deleting, or executing arbitrary code. The batch verification process is inherently a lookup/validation operation (read) rather than a write, execute, or destructive action.
From the tool's definition Tool performs verification of email addresses and returns status/score - a read-only operation with no modification or deletion of data. The description contains no language indicating mutations, side effects, or irreversible actions.
Attacks that exploit this kind of access
Verify multiple email addresses in batch (max 25). Returns status and score for each. It is categorised as a Read tool in the Prospector MCP MCP Server, which means it retrieves data without modifying state.
Register the Prospector MCP server in PolicyLayer and add a rule for verify_emails_batch: 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 Prospector MCP. Nothing to install.
verify_emails_batch 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 verify_emails_batch 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 verify_emails_batch. 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.
verify_emails_batch is provided by the Prospector MCP server (josiebot26/prospector-mcp-email-finder). 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 →