Get started

Bouncer for AI agents

Bouncer is an email verification service that marketing teams use to check whether addresses are deliverable before sending campaigns, one at a time or in bulk. 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.

Connect BouncerSee the 10 actions ↓
EmailAPI keyMCP + RESTusebouncer.com
AUDIT LOG · BOUNCERPOLICY: acme-support
09:41:07 · claude · u_8f2read
bouncer.get_credits
Get Credits✓ allowed · 212ms
09:41:08 · claude · u_8f2read
bouncer.verify_email
Verify Email✓ allowed · 164ms
09:41:09 · claude · u_8f2write
bouncer.create_batch_request
Create Batch Request✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
bouncer.delete_batch_request
Delete batch request✕ blocked · policy: deny
EVERY BOUNCER CALL, ON THE RECORD
01 · USE CASES

What agents do in Bouncer.

01

Verify a single email address

Run a real-time check on one email address to confirm it is deliverable before it gets used.

02

Run a bulk verification batch

Create a batch request to verify a list of addresses after the user confirms the credit cost.

03

Require approval before deleting a batch

Treat deleting a batch or toxicity list job as destructive since it removes verification history.

02 · ACTIONS

10 Bouncer actions, graded by risk.

Every Bouncer action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

5

Look things up. Allowed by default.

  • bouncer.get_credits
    Get Credits
  • bouncer.get_batch_results
    Get Batch Results
  • bouncer.verify_email
    Verify Email
  • bouncer.verify_domain
    Verify Domain
  • bouncer.check_toxicity_list_job_status
    Check Toxicity List Job Status

write

3

Create and change things. Allow, or ask the user first.

  • bouncer.create_batch_request
    Create Batch Request
  • bouncer.create_toxicity_list_job
    Create Toxicity List Job
  • bouncer.finish_batch
    Finish Batch

destructive

2

Delete, cancel or archive. Ask first, or deny outright.

  • bouncer.delete_batch_request
    Delete batch request
  • bouncer.delete_toxicity_list_job
    Delete Toxicity List Job
03 · HOW IT WORKS

Bouncer in three steps.

  1. 01Your users connect BouncerThey add their Bouncer api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Batch Request” can wait for the user, and “delete batch request” can be denied outright.
  3. 03Any agent can actYour agent calls Bouncer through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('bouncer', {
  read: 'allow',
  write: 'ask',        // create_batch_request
  destructive: 'deny',  // delete_batch_request
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Bouncer connects.

Users add their Bouncer 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 Bouncer 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
05 · WORKS WITH

Use Bouncer from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More email apps.

Gmail62 actionsOutlook306 actionsSendGrid364 actionsMixmax94 actionsElastic Email91 actionsResend66 actionsLettr60 actionsPostmark46 actions
ALL EMAIL APPS →
07 · FAQ

Bouncer and Arc0, answered.

Q01

Can I use Bouncer with Claude, ChatGPT or Cursor?

Yes. Connect Bouncer 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 Bouncer actions you allow.

Q02

How do users connect Bouncer?

Users add their Bouncer 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.

Q03

Which Bouncer actions can my agent take?

10 in total: 5 read, 3 write and 2 destructive, such as “create Batch Request”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Bouncer?

Yes. Actions like “delete batch request” 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.

Q05

Can my own backend call Bouncer too?

Yes. The same Bouncer connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Bouncer into your agent.

Your users connect Bouncer once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.

Connect BouncerBrowse all apps →

Free to build · MCP + REST · Audit log on every plan