Validate an email address: RFC syntax validity, normalized address with local/domain, and flags for isDisposable (throwaway domain), isRoleAccount (info@/support@/…), isFreeProvider (gmail/outlook/…). With checkMx (default true) also reports hasMxRecords (domain MX presence, via DNS-over-HTTPS) +...
AI agents call email.validate to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a validation and information-retrieval tool. It queries email syntax, performs DNS lookups for MX records, and returns classification flags—all read-only operations with no capability to modify, delete, execute code, or affect financial state. The explicit disclaimer that it provides 'signals only' and makes no guarantees confirms it is purely informational.
From the tool's definition Tool description explicitly states it 'Validate[s] an email address' and 'reports' on syntax, normalization, disposability flags, and MX records. It performs DNS queries (DNS-over-HTTPS for MX records) and analysis only.
Attacks that exploit this kind of access
Validate an email address: RFC syntax validity, normalized address with local/domain, and flags for isDisposable (throwaway domain), isRoleAccount (info@/support@/…), isFreeProvider (gmail/outlook/…). With checkMx (default true) also reports hasMxRecords (domain MX presence, via DNS-over-HTTPS) + MX hosts. NOT a deliverability or mailbox-existence guarantee — signals only. For signup hygiene and lead scrubbing. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for email.validate: 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 Mcp. Nothing to install.
email.validate 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 email.validate 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 email.validate. 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.
email.validate is provided by the MCP server (@2sio/mcp). 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 →