Integration

AgentQL integration

AgentQL (by TinyFish) extracts structured JSON from web pages and documents with AI: describe the data you want as an AgentQL query or a plain-language prompt, point it at a public URL or raw HTML, and get back data shaped like your query. It also reads PDFs and images (JPEG, PNG) uploaded as files, and reports the API call usage of the key and the account and the usage of remote browser sessions. Creating a Tetra remote browser session is not exposed: it returns a Chrome DevTools websocket address that only a browser-automation client such as Playwright can drive, and the unversioned duplicates of the v1 routes are left out. Billed per API call (one per web query, one per image or PDF page). Authentication is an API key from the AgentQL Dev Portal sent in the X-API-Key header.

Connect AgentQL How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

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

What you can do with AgentQL

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.

Browser session, 1 operation

list_browser_session_usageList browser session usageGETLists usage records of Tetra remote browser sessions on the account (start and end time, duration, browser profile, proxy traffic, status), newest first by default, one page at a time.

Document, 1 operation

query_documentQuery documentPOSTExtracts structured data from an uploaded PDF or image file (JPEG, PNG) with an AgentQL query or prompt. Billed: one API call per image and one per PDF page (a 10-page PDF uses 10 calls).

Usage, 1 operation

get_usageGet usageGETReturns AgentQL API call usage for this API key and for the whole account (current billing cycle and lifetime), with the current subscription's cycle dates and usage limits.

Web page, 1 operation

query_web_pageQuery web pagePOSTExtracts structured data from a public web page (url) or raw HTML (html) with an AgentQL query or a plain-language prompt, and returns it shaped like the query. Billed: one AgentQL API call per request.

Use AgentQL from Claude Code, Cursor or Codex

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

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