Verifly

Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.

Email verification for AI agents — verify, clean & validate emails; self-onboard + crypto pay

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Verifly": {
      "url": "https://verifly.email/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (17)

• get_started read-only

  Call this FIRST if you have no Verifly API key. Returns how Verifly works and how to get access with no human: pay-as-you-go email verification API, 100 free credits on self-registration, no monthly fee. No API key required to call this tool.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• verify_email_demo read-only

  Verify one email address with NO account or API key, so you can evaluate Verifly before registering. Rate-limited per IP (a few checks). Returns the same deliverability verdict and flags as the full API. For real volume, call register_account for a key + 100 free credits, then use verify_email.

  Parameters:

  • email (required) — string — The email address to verify, e.g. [email protected]

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• verify_email read-only

  Verify one email address in real time. Returns a deliverability verdict (valid / invalid / risky / unknown), the reason, detailed flags (disposable, role account, catch-all, MX, SMTP), a send/reject recommendation, and credit usage.

  Parameters:

  • email (required) — string — The email address to verify, e.g. [email protected]

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• verify_batch read-only

  Synchronously verify a list of email addresses (best for up to a few hundred). Returns a per-address verdict for each email. For very large lists use the bulk async endpoint instead.

  Parameters:

  • emails (required) — array — Array of email addresses to verify.
  • exclude_role_accounts — boolean — Flag/exclude role accounts (info@, sales@, ...). Default false.
  • exclude_public_domains — boolean — Flag/exclude public domains (gmail.com, ...). Default false.

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• clean_email_list read-only

  Clean a list of email addresses before an import or campaign: dedupes, removes invalid syntax, and (optionally) strips disposable and role accounts. Returns the cleaned list plus a summary of what was removed.

  Parameters:

  • emails (required) — array — Email addresses to clean.
  • remove_disposable — boolean — Remove disposable/throwaway addresses. Default true.
  • exclude_role_accounts — boolean — Remove role accounts (info@, support@, ...). Default false.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• extract_emails read-only

  Extract all email addresses found in a block of free-form text (notes, pasted documents, signatures). Optionally deduplicates and lowercases the results.

  Parameters:

  • text (required) — string — Free-form text to scan for email addresses.
  • lowercase — boolean — Lowercase all extracted addresses. Default true.
  • deduplicate — boolean — Remove duplicate addresses. Default true.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• check_domain_health read-only

  Check the DNS and deliverability health of an email domain: MX records, SPF, DMARC, and an overall health score. Useful for diagnosing why a domain bounces or for validating a sending domain.

  Parameters:

  • domain (required) — string — Domain to check, e.g. example.com

  Hints: read-only yes · destructive no · idempotent not declared · open-world yes

• get_credits read-only

  Return the API key's remaining verification credits and recent usage (today / this month) and plan. Costs no credits.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• submit_bulk

  Submit a list of email addresses as an asynchronous bulk verification job — the right tool for large lists. Returns immediately with a job_id, status, and the check_status_url / results_url to poll. Small lists may complete inline (status 'completed'); larger ones return status 'pending' — poll get_job_status until it is 'completed', then call get_job_results. Optionally register a webhook_url (public HTTPS) to be notified when the job finishes.

  Parameters:

  • emails (required) — array — Email addresses to verify in this job (deduped server-side).
  • webhook_url — string — Optional public HTTPS URL to POST a job.completed notification to.

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• get_job_status read-only

  Fetch the current status and progress of a bulk verification job by its job_id (status, percent progress, processed count, and a valid/invalid/risky summary). Poll this after submit_bulk until status is 'completed', then call get_job_results.

  Parameters:

  • job_id (required) — string — The job_id returned by submit_bulk.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_job_results read-only

  Fetch the full per-address results of a completed bulk verification job by job_id (each email's verdict, recommendation, and reason) plus the valid/invalid/risky summary and credits used. The job must be 'completed' — check get_job_status first.

  Parameters:

  • job_id (required) — string — The job_id returned by submit_bulk.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• list_jobs read-only

  List the account's bulk verification jobs, most recent first, with their status, progress, and summary. Optionally filter by status and paginate. Use this to find past jobs and their job_ids.

  Parameters:

  • limit — integer — Max jobs to return (1-100, default 50).
  • offset — integer — Pagination offset (default 0).
  • status — string — Only return jobs in this status.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_usage read-only

  Return detailed usage statistics for the account over a period (day, week, or month): total credits used, emails processed, request counts broken down by endpoint and source, a daily breakdown, and recent activity.

  Parameters:

  • limit — integer — Max recent log entries to include (default 100, max 1000).
  • period — string — Reporting period. Default 'month'.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_account read-only

  Return the account profile for the current API key: email, name, company, timezone, remaining credits, total credits used, number of API keys, and plan. Costs no credits.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• get_packages read-only

  List the credit packages available for purchase (id, name, credit amount, price in USD, and price per 1k credits). Use the returned package id with buy_credits.

  Hints: read-only yes · destructive no · idempotent not declared · open-world no

• buy_credits

  Start a purchase of a credit package and return a way to pay. This does NOT complete a payment by itself — it returns a payment link / address: • method 'stripe' → returns a checkout_url. Paying by card requires a HUMAN to open that link and enter card details; an agent cannot finish a card payment on its own. • method 'crypto' → returns a Plisio invoice with a checkout_url AND, when you pass a `currency` (BTC, ETH, LTC, USDT, USDC), a RAW wallet `address` + `amount`. An autonomous agent CAN pay this from a crypto wallet with no browser/human, then credits are added automatically once the payment confirms. Prefer crypto for fully autonomous top-ups. Get a package id from get_packages first.

  Parameters:

  • package_id (required) — string — The package id to buy (from get_packages).
  • method — string — Payment method. 'stripe' = card link (needs a human), 'crypto' = wallet-payable invoice. Default 'stripe'.
  • currency — string — For method 'crypto': the coin to pay in; returns a raw wallet address an agent can pay autonomously.

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• register_account

  Programmatically create a brand-new Verifly account — this is how an agent self-onboards with no human in the loop. Requires only an email and a password (min 8 chars; disposable email domains are rejected). The new account starts with free credits. The response includes the new account id/email and a freshly generated `api_key.key` that is shown ONCE — capture and store it immediately, it cannot be retrieved again. Subsequent tool calls can then use that key as the bearer token.

  Parameters:

  • email (required) — string — Email for the new account (not a disposable domain).
  • password (required) — string — Password for the new account (minimum 8 characters).

  Hints: read-only no · destructive no · idempotent not declared · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.