Integration

Thordata SERP API integration

Thordata's SERP API runs live web searches on Google, Bing, Yandex and DuckDuckGo from real devices and proxies and returns each results page parsed as JSON (organic results, knowledge panels, people also ask, news, images, related searches, pagination; Google can add its AI Overview). Only searches answered with status 200 are billed, and an identical search repeated within 5 minutes is served free from cache. Thordata's other engines (Google News, Images, Maps, Shopping, Jobs, Scholar, Flights, Hotels, Trends, Lens, Play, Finance, Patents, AI Mode, Bing verticals) are not exposed because their answers are undocumented, nor are the token usage query, the Universal Scraping, WebPage and Web Scraper APIs and the proxy products, which use other credentials. Authentication is the SERP API token from the Thordata dashboard (SERP API, API Playground, Token), sent as a Bearer token.

Connect Thordata SERP API How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

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

What you can do with Thordata SERP API

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.

bing_searchBing searchPOSTAgents: ask firstRuns a live Bing web search through Thordata and returns the parsed results page: organic results, ads, images, videos, news, people also ask, related searches and pagination. Billed per successful search.
duckduckgo_searchDuckduckgo searchPOSTAgents: ask firstRuns a live DuckDuckGo web search through Thordata and returns the parsed results page: organic results, related searches and the knowledge summary. Billed per successful search.
google_searchGoogle searchPOSTAgents: ask firstRuns a live Google web search through Thordata and returns the parsed results page: organic results, local results, people also ask, top stories, knowledge panel, AI Overview (with ai_overview) and pagination. Billed per successful search.
yandex_searchYandex searchPOSTAgents: ask firstRuns a live Yandex web search through Thordata and returns the parsed results page: organic results, images, related searches and the knowledge panel. Pass the query in text. Billed per successful search.

Use Thordata SERP API from Claude Code, Cursor or Codex

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

Create your workspace
Sign up free. Nothing to install.
Connect Thordata SERP API once
Add your Thordata SERP API 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.