Mails.so for AI agents
Mails.so is an email validation API that checks single and bulk addresses to keep mailing lists clean and deliverable before a campaign send. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Mails.so.
Validate a single email
Check one email address for deliverability before it enters an outreach sequence.
Validate a bulk list
Submit a batch of addresses for validation before a list import, so only deliverable ones make it through.
Check batch validation results
Retrieve the results of a submitted bulk validation job to see which addresses passed, a read-only lookup.
3 Mails.so actions, graded by risk.
Every Mails.so action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- mails_so.validate_bulk_emailsValidate Bulk Emails
- mails_so.validate_single_emailValidate Single Email
- mails_so.retrieve_batch_resultsRetrieve Batch Results
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Mails.so in three steps.
- 01Your users connect Mails.soThey add their Mails.so api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Mails.so through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('mails_so', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Mails.so connects.
Users add their Mails.so api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Mails.so connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Mails.so from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Mails.so and Arc0, answered.
Can I use Mails.so with Claude, ChatGPT or Cursor?
Yes. Connect Mails.so to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Mails.so actions you allow.
How do users connect Mails.so?
Users add their Mails.so api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Mails.so actions can my agent take?
3 in total: 3 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Mails.so?
Yes. Allow read actions and deny writes in the Mails.so policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Mails.so too?
Yes. The same Mails.so connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Mails.so into your agent.
Your users connect Mails.so once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan