DeBounce for AI agents
DeBounce validates email addresses and processes bulk lists, helping a marketing team keep bounce rates down before a campaign goes out. 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 DeBounce.
Validate a single email
Validate a single email address before adding it to an active sending list.
Check a bulk validation job
Check the status of a bulk validation job before pulling in the cleaned list.
Check remaining account balance
Check the remaining account balance before submitting another batch of email validations.
4 DeBounce actions, graded by risk.
Every DeBounce action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- debounce.get_api_usageGet API Usage
- debounce.get_account_balanceGet Account Balance
- debounce.get_bulk_validation_statusGet Bulk Validation Status
- debounce.validate_emailValidate Email
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.
DeBounce in three steps.
- 01Your users connect DeBounceThey add their DeBounce 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 DeBounce through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('debounce', { 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 DeBounce connects.
Users add their DeBounce 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 DeBounce 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 DeBounce from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
DeBounce and Arc0, answered.
Can I use DeBounce with Claude, ChatGPT or Cursor?
Yes. Connect DeBounce 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 DeBounce actions you allow.
How do users connect DeBounce?
Users add their DeBounce 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 DeBounce actions can my agent take?
4 in total: 4 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in DeBounce?
Yes. Allow read actions and deny writes in the DeBounce policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call DeBounce too?
Yes. The same DeBounce connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug DeBounce into your agent.
Your users connect DeBounce once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan