Integration

Tiny Talk AI integration

Tiny Talk AI hosts customer-facing AI agents (chatbots) trained on your own knowledge base and embedded on websites, WhatsApp or Slack. This integration sends a conversation to one of your agents and returns its reply, with token usage and the knowledge-base pages it cited, for example to answer customer questions from a workflow. On plans with AI credits each reply consumes credits (most models 1, premium models 2 to 10). Knowledge-base, agent settings and help desk management are not exposed by Tiny Talk's API. Authentication is an API key created in the dashboard on the agent (select it, then Integrations, Hub, Tiny Talk), sent in the api-key header; it is required for private agents and lifts the per-user rate limit on public ones.

Connect Tiny Talk AI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Tiny Talk AI.Built from the 1 Tiny Talk AI tool below, on the connection you add once.

What you can do with Tiny Talk AI

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.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

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

ask_agentAsk agentPOSTAgents: ask firstSends a conversation to a Tiny Talk agent and returns its full reply (choices[0].message.content), token usage and cited knowledge-base pages. Each call generates a new AI reply and uses AI credits.

Use Tiny Talk AI from Claude Code, Cursor or Codex

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

Create your workspace
Sign up free. Nothing to install.
Connect Tiny Talk AI once
Add your Tiny Talk AI 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.