Mail7 for AI assistants
Email validation MCP server for Claude and other AI assistants
Connect Mail7 to your assistant through the Model Context Protocol and it can verify an address, clean a list of signups or explain why your mail lands in spam, without you opening another tab. Use the hosted endpoint with nothing to install, or run it locally from npm.
Available now on npm as mail7-mcp, and listed in the official MCP registry as net.mail7/email-validation. Nothing to install by hand - npx fetches it when your assistant starts.
How it behaves
Four tools your assistant can call
The server hands the model a small, sharp toolkit. It decides when to reach for each one:
validate_email
One address: syntax, MX records, disposable-domain database and a live SMTP mailbox probe.
validate_emails
Up to 50 addresses per call, returned with a per-address verdict and a summary count.
check_domain
A graded audit of MX, SPF, DKIM, DMARC, MTA-STS, TLS-RPT, DNSSEC and BIMI, with a fix for each problem.
check_spf
The SPF record itself: mechanisms, lookup count and the misconfigurations that break alignment.
An assistant that will not throw away good addresses
A language model asked to clean a list tends to treat anything uncertain as junk. Mail7 answers in three states, and every tool description says in plain words what the middle one means, so the model keeps what it could not confirm:
What you can ask for
Once the server is connected, the work happens in ordinary sentences:
- Is [email protected] a real mailbox?
- Take the signups in this CSV and tell me which ones will bounce.
- Our newsletter keeps landing in spam - check what is wrong with our domain.
- Before I import these leads into the CRM, drop the confirmed-invalid ones.
Two ways to connect
Pick whichever suits your assistant. Both expose the same four tools.
Paste this URL into your assistant's connector settings:
https://mail7.net/mcp
Works in clients that support remote MCP servers. No Node, no config file, nothing to keep updated.
One command in Claude Code:
claude mcp add mail7 --env MAIL7_API_KEY=your_key -- npx -y mail7-mcp
Claude Desktop, Cursor, Windsurf and Cline take the same command in their JSON config. Needs Node 18 or newer.
Single checks and domain audits work without a key in both cases, at 5 checks per minute. Cleaning a list differs: the hosted endpoint requires an API key, because it sees your assistant provider's address rather than yours and cannot meter anonymous bulk fairly. The local package still gives you a 25-address free sample. Then just ask in plain language - the assistant picks the right tool by itself.
Questions
Frequently asked questions
What is an MCP server?
Model Context Protocol is an open standard for connecting AI assistants to external tools. An MCP server exposes a set of tools that the assistant can call on its own, so Claude or Cursor can validate an email without you leaving the chat.
Do I have to install anything?
No, if your assistant supports remote MCP servers: point it at https://mail7.net/mcp and that is the whole setup. The npm package is there for clients that run servers locally, and even then npx fetches it on demand.
Is it in the official MCP registry?
Yes, as net.mail7/email-validation. The name is held through ownership of the mail7.net domain, not a personal account, and every release is published from CI with a provenance attestation linking the package to the commit it was built from.
Which AI assistants does it work with?
Any MCP client. That includes Claude Desktop, Claude Code, Cursor, Windsurf, Cline and Zed.
Do I need an API key?
Not for single checks, SPF or domain audits - those run anonymously at 5 checks per minute. Cleaning a list through the hosted endpoint does need one, because the server sees your assistant provider's shared address instead of yours. Keys are created in your Mail7 account.
Will the assistant delete addresses it could not verify?
No. Every tool description states that Unknown means unverifiable, not invalid, and instructs the model to keep those addresses and present them separately.
How many addresses can it check at once?
Up to 50 per call with the npm package and 25 through the hosted endpoint, which has to finish inside the proxy's request timeout. Each address is a live SMTP conversation, so the assistant works through a longer list in chunks rather than in one request.
Are Unknown results billed?
No. You are charged only for definite Valid and Not Valid results; Unknown checks are always free.
Related integrations
Free single checks, paid plans for volume
Single checks are free and need no account. Paid plans raise your rate limit and unlock full list cleaning, and you are only charged for definite Valid and Not Valid results. Unknown checks are always free.