Communication
respond.io for AI agents.
Managed auth, ready-made tools.
Find and update contacts, tag them, send messages and close conversations in respond.io on behalf of each of your users.
About respond.io
With the respond.io connector, your agent works in each user’s own respond.io workspace. It can find, create or update a contact, add tags, send a message on a connected channel and close a conversation, using only the tools your project allows.
respond.io is a customer conversation platform that brings chat apps like WhatsApp, Messenger and email into one inbox.
Tools
What your agent can do in respond.io.
Each tool is a capability the model can call. You decide which ones a project allows, and every call runs with the end user's own respond.io connection.
-
Get a contact
Readrespond_io_get_contactRead a contact by ID, email or phone number.
-
Create a contact
Writerespond_io_create_contactAdd a new contact.
-
Update a contact
Writerespond_io_update_contactChange a contact's fields.
-
Add tags
Writerespond_io_add_tagsAdd tags to a contact.
-
Send a message
Writerespond_io_send_messageSend a message to a contact on a connected channel.
-
Close a conversation
Writerespond_io_close_conversationClose a contact's open conversation.
No tool matches that search.
Control
Limits you can set.
You decide what your agent may do in respond.io, and Agent200 runs every call within those limits.
-
Turn single tools on or off
Let the agent read and tag contacts, and switch off
respond_io_send_messageso it can never message a customer. -
Restrict what the agent reaches
Choose the endpoints a project may use, for example contacts but not messaging. A call outside them is refused.
Get started
Connect respond.io
in three steps.
-
1
Set up the SDK
Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.
agent.jsConceptual exampleSet up the SDK with the Agent200 API key // One Agent200 API key covers every connector enabled for the project. const agent200 = new Agent200({ apiKey: process.env.AGENT200_API_KEY, }); -
2
Let your user connect respond.io
Each end user authorizes their own respond.io account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.
connect.jsConceptual exampleLet an end user connect their account (managed OAuth) // Each end user authorizes their own respond.io account, once. const connection = await agent200 .user("user_123") .connect("respond_io"); if (connection.authorizationUrl) { // Show this link to your user; Agent200 handles the rest. console.log(connection.authorizationUrl); } -
3
Run with the respond.io tools
Name the user, the model and the tools. The model decides which respond.io tools to call, and Agent200 executes them with that user's connection.
run.jsConceptual exampleRun a request with the connector's tools const result = await agent200 .user("user_123") .run({ model: "openai/gpt-5.6-sol", input: "Tag the contact +44 7700 900123 as VIP", tools: ["respond_io"], }); console.log(result.output);
Access
Sign-in and permissions.
-
Who signs in
Each of your users, once, connecting their own respond.io workspace. Each connection belongs to that user.
-
What access is requested
Access to the parts of their respond.io workspace the connection needs, such as contacts, messages and conversations. Users can revoke it later from their respond.io workspace settings.
For agents
Instructions for AI agents.
Using a coding agent? Paste this brief into it, or give it the address of this page. It describes the respond.io connector and how to use it.
Connector: respond.io, through Agent200. In code: "respond_io". What it does: Find and update contacts, tag them, send messages and close conversations in respond.io on behalf of each of your users. Page: https://www.agent200.com/connectors/respond-io/ 1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs. 2. Sign-in is managed OAuth. Each end user approves access once, on respond.io's own page, through the authorization link Agent200 returns. Never ask a user for a respond.io password or token in chat. 3. Give every request a stable id for the end user. Agent200 uses only that user's own connection. 4. Read tools: respond_io_get_contact. Write tools: respond_io_create_contact, respond_io_update_contact, respond_io_add_tags, respond_io_send_message, respond_io_close_conversation. Name "respond_io" in the tools of a request; the model decides which tool to call. 5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it. 6. Before a write, confirm with the user, unless they asked for that exact change. 7. For setup with a specific framework, follow its guide: https://www.agent200.com/connectors/respond-io/framework/claude/ https://www.agent200.com/connectors/respond-io/framework/chatgpt/ https://www.agent200.com/connectors/respond-io/framework/claude-code/ https://www.agent200.com/connectors/respond-io/framework/muse/ https://www.agent200.com/connectors/respond-io/framework/grok-bot/ https://www.agent200.com/connectors/respond-io/framework/openai-dots/ https://www.agent200.com/connectors/respond-io/framework/claude-duet/ https://www.agent200.com/connectors/respond-io/framework/hermes-agent/ https://www.agent200.com/connectors/respond-io/framework/openclaw/ The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/
This page is also available as Markdown, for agents and LLMs: /connectors/respond-io.md
Guides
Use respond.io with the AI you build on.
Step-by-step setup for respond.io with a specific model, assistant or agent framework.
-
respond.io + Claude
How to connect respond.io to Claude
-
respond.io + ChatGPT
How to connect respond.io to ChatGPT
-
respond.io + Claude Code
How to connect respond.io to Claude Code
-
respond.io + Muse
How to connect respond.io to Muse
-
respond.io + Grok Bot
How to connect respond.io to Grok Bot
-
respond.io + OpenAI Dots
How to connect respond.io to OpenAI Dots
-
respond.io + Claude Duet
How to connect respond.io to Claude Duet
-
respond.io + Hermes Agent
How to connect respond.io to Hermes Agent
-
respond.io + OpenClaw
How to connect respond.io to OpenClaw
FAQ
respond.io and Agent200, answered.
Who handles the respond.io OAuth flow and the tokens?
Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for respond.io.
Does my agent act as the end user?
Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's respond.io connection, never another user's. It cannot reach anything the user or respond.io has not authorized.
Can I limit what my agent can do in respond.io?
Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.