Email, phone and IP verification API MCP server

Which MCP servers are Email, phone and IP verification API's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-28

← Back to Email, phone and IP verification API

Whose server it is

Registry namenet.verified/verifiedverified in the MCP registry

The registry name sits under verified.net. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-28

Stateanswerschecked 2026-10-28
Tools11
Server calls itselfVerified.net
Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 159 ms.

Should an agent connect itNot proven either way yet

Its tools do every use case we checked: reject fake signups using email, phone and IP checks; verify email mailboxes and flag disposable addresses; check phone line type and carrier porting status.
Checked on 6 of the 7 days it takes to judge reliability.

Once connected

For "reject fake signups using email, phone and IP checks", the likely first call is verify_email.
For "verify email mailboxes and flag disposable addresses", the likely first call is verify_email.
For "check phone line type and carrier porting status", the likely first call is carrier_lookup.
create_bulk_job change data without a sign-in: anyone with the address can call them.
Parameters are untyped or undescribed in 10 of 11 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 6, the first on 2026-10-28

INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
What an agent can do with it3 of 3 use cases
Answeredmeasuring6 of the 7 daily checks it takes to print a share
Median first answer155 ms
Space in an agent's context≈ 1,334 tokensthe definitions of all its tools (11), which an agent carries on every turn
Tool definitionsB · 85 of 100
Typed results0 of 11 toolsdeclared outputSchema: results come typed, read once

Parameters without a description: in 10 of 11

What an agent can do with it

can do · reject fake signups using email, phone and IP checks
can do · verify email mailboxes and flag disposable addresses
can do · check phone line type and carrier porting status

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

Tools that change data, on a server that answers without a sign-in: create_bulk_job

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers11 tools · read 2026-10-28

verify_email
Check an email address: syntax, mail server, mailbox (when the server allows), disposable, role account, typo suggestion, risk score and an accept/review/reject recommendation. 1 credit.
validate_phone
Check a phone number: validity, E.164 format, line type, region, time zone, original carrier assignment (US), VoIP, risk score and recommendation. Numbers without + need default_country (e.g. "US"). 1 credit.
carrier_lookup
US/Canada numbers: the carrier serving the number today, whether it was ported, port date, current line type and VoIP, from a live number-portability lookup. 3 credits; not charged if unavailable.
ip_lookup
Check an IPv4/IPv6 address: approximate location, network owner (ASN), Tor exit, datacenter/hosting, risk score and recommendation. 1 credit.
verify_contact
Check whether a name and/or phone match the domain registration records that list this email. Returns match levels only (match / partial / no_match), never the records. 1 credit.
reverse_phone
Who is behind a US/Canada phone number. standard: caller ID name (10 credits if found). premium: caller ID plus names, emails and phones from domain registration records (25 if contacts are found, 10 if only a caller ID). Nothing found…
reverse_email
Who is behind an email address: names and phone numbers from domain registration records. 10 credits if found, free otherwise.
create_bulk_job
Check up to 100,000 values in the background, charged per unique value like single lookups (reverse lookups only when found). Returns the job; poll get_bulk_job, then get_bulk_results.
get_bulk_job
Status and progress of a bulk job. Free.
get_bulk_results
Results of a bulk job, one page at a time (has_next tells you to ask for the next page). Free.
get_account
Your credit balance and usage today and over the last 30 days. Free.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "verified": {
      "type": "http",
      "url": "https://api.verified.net/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http verified https://api.verified.net/mcp

Add to Cursor Add to VS Code

claude.ai, ChatGPT and other clients: add https://api.verified.net/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.