Re:amaze for AI agents
Re:amaze is a multi-channel customer support platform offering live chat, email, and social messaging with automated workflows. Support teams use it to manage every customer channel in one inbox. 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 Re:amaze.
Check response templates read-only
Look up saved response templates before replying to a common customer question.
Check report tags read-only
Pull report tags to see how conversations are being categorized this period.
Review tags before reclassifying conversations
Check existing tags read-only before deciding how to reorganize the support inbox.
2 Re:amaze actions, graded by risk.
Every Re:amaze 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.
- re_amaze.get_reports_tagsGet report tags
- re_amaze.get_response_templatesGet Response Templates
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.
Re:amaze in three steps.
- 01Your users connect Re:amazeThey add their Re:amaze 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 Re:amaze through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('re_amaze', { 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 Re:amaze connects.
Users add their Re:amaze 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 Re:amaze 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 Re:amaze from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Re:amaze and Arc0, answered.
Can I use Re:amaze with Claude, ChatGPT or Cursor?
Yes. Connect Re:amaze 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 Re:amaze actions you allow.
How do users connect Re:amaze?
Users add their Re:amaze 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 Re:amaze actions can my agent take?
2 in total: 2 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Re:amaze?
Yes. Allow read actions and deny writes in the Re:amaze policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Re:amaze too?
Yes. The same Re:amaze connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Re:amaze into your agent.
Your users connect Re:amaze 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