NeverBounce for AI agents
NeverBounce is an email verification service that checks address validity in bulk or in real time to reduce bounce rates. 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 NeverBounce.
Check a single email address
Verify one email address's deliverability before it goes into an outreach sequence.
Check a bulk job's results
Retrieve results from a completed bulk verification job to see which addresses are safe, a read-only lookup.
Approve before deleting a job
Require approval before deleting a verification job, since it removes its stored results.
12 NeverBounce actions, graded by risk.
Every NeverBounce action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- neverbounce.search_jobsSearch bulk verification jobs
- neverbounce.parse_jobParse NeverBounce Job
write
9Create and change things. Allow, or ask the user first.
- neverbounce.jobs_startStart NeverBounce Job
- neverbounce.confirm_poeConfirm Proof of Email
- neverbounce.jobs_createCreate NeverBounce Bulk Verification Job
- neverbounce.jobs_statusGet bulk job status
- neverbounce.account_infoGet Account Info
- neverbounce.jobs_resultsRetrieve Job Results
- neverbounce.single_checkNeverBounce Single Check
- neverbounce.jobs_download_getDownload Job Results (GET)
- neverbounce.widget_send_eventJS Widget Send Event
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- neverbounce.jobs_deleteDelete NeverBounce Job
NeverBounce in three steps.
- 01Your users connect NeverBounceThey add their NeverBounce api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “start NeverBounce Job” can wait for the user, and “delete NeverBounce Job” can be denied outright.
- 03Any agent can actYour agent calls NeverBounce through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('neverbounce', { read: 'allow', write: 'ask', // jobs_start destructive: 'deny', // jobs_delete }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How NeverBounce connects.
Users add their NeverBounce 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 NeverBounce 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 NeverBounce from any agent.
NeverBounce and Arc0, answered.
Can I use NeverBounce with Claude, ChatGPT or Cursor?
Yes. Connect NeverBounce 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 NeverBounce actions you allow.
How do users connect NeverBounce?
Users add their NeverBounce 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 NeverBounce actions can my agent take?
12 in total: 2 read, 9 write and 1 destructive, such as “start NeverBounce Job”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in NeverBounce?
Yes. Actions like “delete NeverBounce Job” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.
Can my own backend call NeverBounce too?
Yes. The same NeverBounce connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug NeverBounce into your agent.
Your users connect NeverBounce once, under your brand. Your agent gets 12 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan