Integration

ChatNode integration

ChatNode hosts AI chatbots (agents) trained on a team's files, text and websites. Send a message to a trained agent and get its answer, continue a conversation through its chat session id, list the leads an agent captured (end-user name, email and phone) and read the message history of past conversations. Training, appearance, actions and deployment are configured in the ChatNode app: the API exposes no route for them, and the streaming variant of send_message is not offered. Authentication is a team API key sent as a Bearer token: in ChatNode, open Team Settings, then the API Access tab, and click Generate.

Connect ChatNode How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

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

What you can do with ChatNode

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.

Message, 2 operations

list_chat_messagesList chat messagesPOSTReturns the message history between an agent and its visitors: one entry per message with its session_id, created_at and message (type ai or human, and the text in data.content). Pass session ids to read given conversations.
send_messageSend messagePOSTSends a message to a trained ChatNode agent and returns its reply. Pass the returned chat_session_id back to continue the same conversation; leave it out to start a new one. Each call posts a new message to that conversation.

Lead, 1 operation

list_leadsList leadsPOSTLists the leads captured by an agent: one entry per conversation session, with its session_id, created_at and, when the visitor gave them, the end user's name, email and phone (personal data), plus for_agent.

Team, 1 operation

get_current_teamGet current teamGETChecks that the API key is valid and returns the team it belongs to: its id, name and slug.

Use ChatNode from Claude Code, Cursor or Codex

Connect ChatNode in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its ChatNode 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 ChatNode

Create your workspace
Sign up free. Nothing to install.
Connect ChatNode once
Add your ChatNode 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.