MCP Email Verification for AI Agents

By Aria Pramesi, founder of InboxPolicy · Updated July 4, 2026

InboxPolicy ships an MCP server exposing decide_send, verify_email, batch, and usage as agent tools. An agent asks should I email this address and gets back one of five actions (send, send_with_caution, review, retry_later, avoid), a confidence score, SMTP evidence, and the cost, in a single tool call, no dashboard required.

What tools does the InboxPolicy MCP server expose?

Four tools, all callable directly by an agent without a REST client or dashboard:

• decide_send: runs syntax, MX, and live SMTP checks against InboxPolicy's verification engine, then applies a deliverability policy that turns the evidence into one action (send, send_with_caution, review, retry_later, or avoid), plus a confidence score.
• verify_email: returns the raw syntax, MX, and SMTP evidence for one address without the policy layer, for agents that want to apply their own decision logic.
• batch: submits a list of addresses and returns per-item results; async batches scale to 50,000 emails with a signed completion webhook when done.
• usage: reports call counts and remaining credits, so an agent can check its own balance before running a large batch.

How do I connect the MCP server to my agent?

Add InboxPolicy to your agent's mcpServers config block, the same pattern used for any other MCP server:

{
  "mcpServers": {
    "inboxpolicy": {
      "command": "npx",
      "args": ["-y", "@inboxpolicy/mcp-server"]
    }
  }
}

Once connected, the agent sees decide_send, verify_email, batch, and usage as first-class tools it can call mid-conversation, no separate API key setup required if it pays per call over x402.

What does an agent get back from a single call?

A decide_send call for one address returns an action, a confidence score, the SMTP evidence behind it, and the cost of that call, for example:

{
  "action": "review",
  "confidence": 0.62,
  "evidence": {
    "syntax_valid": true,
    "mx_found": true,
    "smtp_response": "catch-all domain, mailbox existence unconfirmed"
  },
  "cost_usd": 0.01
}

The agent does not have to parse a status enum and guess what it means for send timing. It gets the decision directly.

How does pricing work for agent calls?

Fresh verifications cost $0.01 each, paid per call over the x402 protocol: USDC on Base, no account and no API key needed. A keyless request gets an HTTP 402 with machine-readable payment requirements, the agent attaches an X-PAYMENT header, and gets its decision plus an on-chain settlement receipt back.

For agents or teams that prefer paying by card up front, prepaid credit packs are available: Starter $5 for 1,000 credits ($5.00/1k), Builder $19 for 5,000 ($3.80/1k), Growth $79 for 25,000 ($3.16/1k). Volume pricing is available on request. Three things are always free regardless of plan: re-verifying the same address within 72 hours (from_cache, 0 credits), rejecting malformed emails before SMTP (0 credits), and retrying with the same idempotency key (never billed twice).

There is no free tier. The $0.01 x402 call is the trial, on purpose, since free tiers tend to attract list-cleaning abuse rather than genuine agent use.

How accurate are the decisions?

On InboxPolicy's prior verification engine, valid-verdict agreement with MillionVerifier was roughly 90% typical across more than 2 million verifications, though this is not a formal recent benchmark and it varies by vertical, dropping as low as 60% in some.

Unknown and catch-all results are never guessed as safe to send, they map to the review action instead. This matters for agents because roughly 30-40% of B2B addresses sit on catch-all domains, where SMTP alone cannot confirm a mailbox exists.

When should an agent use a different tool instead?

InboxPolicy is built for a live send decision inside an agent workflow, not every verification job:

• One-shot cleaning of a huge scraped list at the lowest per-address cost: MillionVerifier's ~$0.59-2.50/1k pricing is built for exactly that.
• Spam-trap and abuse-address detection: ZeroBounce maintains a dedicated spam-trap and abuse database that InboxPolicy does not.
• A dashboard-first marketing suite with CSV uploads and integrations: Kickbox or Emailable are built around that workflow rather than an agent tool call.

Frequently asked questions