Sendbird AI Chatbot for AI agents

Sendbird AI Chatbot lets businesses configure and run automated conversational bots inside Sendbird-powered chat channels for customer engagement and support. 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.

AI and modelsAPI keyMCP + RESTsendbird.com
AUDIT LOG · SENDBIRD AI CHATBOTPOLICY: acme-support
09:41:07 · claude · u_8f2read
sendbird_ai_chatbot.list_bots
List Bots✓ allowed · 212ms
09:41:08 · claude · u_8f2read
sendbird_ai_chatbot.get_bot
Get Bot✓ allowed · 164ms
09:41:09 · claude · u_8f2write
sendbird_ai_chatbot.create_bot
Create Bot✓ approved · approved by user
EVERY SENDBIRD AI CHATBOT CALL, ON THE RECORD
01 · USE CASES

What agents do in Sendbird AI Chatbot.

01

List configured bots

Reads the bots already set up in the workspace before deciding which one to update.

02

Update a bot's configuration

Changes a bot's settings, such as its behavior or connected channels, for a support use case.

03

Create a new bot only after review

Sets up a new chatbot only once its configuration has been reviewed and approved.

02 · ACTIONS

6 Sendbird AI Chatbot actions, graded by risk.

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

read

3

Look things up. Allowed by default.

  • sendbird_ai_chatbot.get_bot
    Get Bot
  • sendbird_ai_chatbot.list_bots
    List Bots
  • sendbird_ai_chatbot.list_group_channels
    List Group Channels

write

3

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

  • sendbird_ai_chatbot.create_bot
    Create Bot
  • sendbird_ai_chatbot.update_bot
    Update Bot
  • sendbird_ai_chatbot.unregister_bot_webhook
    Unregister Bot Webhook

destructive

0

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

  • No destructive actions.
03 · HOW IT WORKS

Sendbird AI Chatbot in three steps.

  1. 01Your users connect Sendbird AI ChatbotThey add their Sendbird AI Chatbot api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “create Bot” can wait for the user to approve.
  3. 03Any agent can actYour agent calls Sendbird AI Chatbot 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('sendbird_ai_chatbot', {
  read: 'allow',
  write: 'ask',        // create_bot
  destructive: 'deny',  
})

# 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 Sendbird AI Chatbot connects.

Users add their Sendbird AI Chatbot 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 Sendbird AI Chatbot 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 Sendbird AI Chatbot from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Sendbird AI Chatbot and Arc0, answered.

Q01

Can I use Sendbird AI Chatbot with Claude, ChatGPT or Cursor?

Yes. Connect Sendbird AI Chatbot 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 Sendbird AI Chatbot actions you allow.

Q02

How do users connect Sendbird AI Chatbot?

Users add their Sendbird AI Chatbot 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 Sendbird AI Chatbot actions can my agent take?

6 in total: 3 read, 3 write and 0 destructive, such as “create Bot”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in Sendbird AI Chatbot?

Yes. Allow read actions and deny writes in the Sendbird AI Chatbot policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call Sendbird AI Chatbot too?

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

Get started

Plug Sendbird AI Chatbot into your agent.

Your users connect Sendbird AI Chatbot once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.

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