Respond.io for AI agents
Respond.io centralizes customer conversations across channels, letting support teams manage contacts, tags, and messages from 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 Respond.io.
Add an internal note
Add an internal comment to a conversation so the next agent has context before replying.
Tag a conversation
Create or update a space tag to route a conversation to the right team.
Check channels before replying
List connected channels to confirm which one a message should go out on.
7 Respond.io actions, graded by risk.
Every Respond.io action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- respond_io.list_usersList users
- respond_io.get_messageGet Message
- respond_io.list_channelsList channels
write
4Create and change things. Allow, or ask the user first.
- respond_io.create_commentAdd internal comment to conversation
- respond_io.create_contactCreate Contact
- respond_io.create_space_tagCreate Space Tag
- respond_io.update_space_tagUpdate Space Tag
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Respond.io in three steps.
- 01Your users connect Respond.ioThey add their Respond.io api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “add internal comment to conversation” can wait for the user to approve.
- 03Any agent can actYour agent calls Respond.io through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('respond_io', { read: 'allow', write: 'ask', // create_comment destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Respond.io connects.
Users add their Respond.io 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 Respond.io 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 Respond.io from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Respond.io and Arc0, answered.
Can I use Respond.io with Claude, ChatGPT or Cursor?
Yes. Connect Respond.io 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 Respond.io actions you allow.
How do users connect Respond.io?
Users add their Respond.io 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 Respond.io actions can my agent take?
7 in total: 3 read, 4 write and 0 destructive, such as “add internal comment to conversation”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Respond.io?
Yes. Allow read actions and deny writes in the Respond.io policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Respond.io too?
Yes. The same Respond.io connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Respond.io into your agent.
Your users connect Respond.io once, under your brand. Your agent gets 7 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan