Kickbox for AI agents
Kickbox is an email verification service that checks addresses in real time and flags disposable or undeliverable ones before a 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 Kickbox.
Verify an email, read-only
Check a single address for deliverability and disposable-domain risk before it goes into an outreach sequence, without sending anything.
Flag disposable signup emails
Check whether a new signup's email domain is disposable so a workflow can route it for review.
Clean a list before import
Run a batch of contact emails through verification so only deliverable addresses reach a marketing list.
2 Kickbox actions, graded by risk.
Every Kickbox action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- kickbox.check_disposableCheck Disposable Email
write
1Create and change things. Allow, or ask the user first.
- kickbox.single_verification_apiKickbox Single Verification
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Kickbox in three steps.
- 01Your users connect KickboxThey add their Kickbox api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “kickbox Single Verification” can wait for the user to approve.
- 03Any agent can actYour agent calls Kickbox through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('kickbox', { read: 'allow', write: 'ask', // single_verification_api destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Kickbox connects.
Users add their Kickbox 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 Kickbox 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 Kickbox from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Kickbox and Arc0, answered.
Can I use Kickbox with Claude, ChatGPT or Cursor?
Yes. Connect Kickbox 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 Kickbox actions you allow.
How do users connect Kickbox?
Users add their Kickbox 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 Kickbox actions can my agent take?
2 in total: 1 read, 1 write and 0 destructive, such as “kickbox Single Verification”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Kickbox?
Yes. Allow read actions and deny writes in the Kickbox policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Kickbox too?
Yes. The same Kickbox connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Kickbox into your agent.
Your users connect Kickbox once, under your brand. Your agent gets 2 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan