Integration

Landbot APIchat integration

Landbot APIchat connects a Landbot bot to a messaging service Landbot does not support natively (Telegram, Slack, SMS, your own app) through an APIchat channel. Push a customer's message (text, location, images, documents, video or audio) into the channel so the bot answers it, create and update the channel's customers, and read an agent's name and avatar. The bot's replies are not returned by these calls: Landbot posts them to the webhook URL set in the channel's settings. The deprecated mark-as-read route is not exposed. Authentication is the channel token from the APIchat channel's settings (not the agent token of the Landbot Platform API), sent in the Authorization header as Token followed by the token.

Connect Landbot APIchat How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Landbot APIchat.Built from the 4 Landbot APIchat tools below, on the connection you add once.

What you can do with Landbot APIchat

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Customer, 2 operations

create_customerCreate customerPOSTCreates a customer in the APIchat channel. Every field is optional; a random token is generated when none is given. Fails with 409 when a customer with the same identifying field exists.
update_customerUpdate customerPUTUpdates a customer of the APIchat channel. Send only the fields to change; null clears a field, and a field left out keeps its value.

Agent, 1 operation

get_agentGet agentGETReturns an agent of the workspace by numeric id: id, name and avatar, for example to show who answered a customer.

Message, 1 operation

send_messageSend messagePOSTSends a message into the APIchat channel as the customer, so the bot handles it and replies to that customer. Creates the customer if the token is unknown. The bot's reply goes to the channel webhook, not this response.

Use Landbot APIchat from Claude Code, Cursor or Codex

Connect Landbot APIchat in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Landbot APIchat operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Landbot APIchat

Create your workspace
Sign up free. Nothing to install.
Connect Landbot APIchat once
Add your Landbot APIchat connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.