Integration

SearchApi integration

SearchApi.io search API. One search call covers dozens of engines, from Google web, news, images, maps, jobs, scholar, shopping, trends, flights and hotels to Bing, Baidu, Yandex, DuckDuckGo, Naver, YouTube and its transcripts, Amazon, eBay, Walmart, the Apple App Store and Google Play, and assistant answers from ChatGPT, Gemini and Perplexity: the engine parameter picks which one. Alongside it, read the credit balance and hourly rate of the account, browse the history of past searches, aggregate usage over time, and look up canonical locations. Every search result carries a json_url pointing at its stored JSON, so the same result can be re-read later without paying for the search again.

Connect SearchApi How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in SearchApi.Built from the 5 SearchApi tools below, on the connection you add once.

Common SearchApi use cases

pulling Google results for a rank tracker
finding which engine drives the credit spend
checking the remaining credits before a large crawl
recovering a result without spending a credit again
resolving a city name before running a local search
charting search volume day by day
auditing what an automation searched for
backing off when the hourly rate is nearly spent
searching a marketplace and a web engine with the same call shape
reading a YouTube transcript through the transcript engine

What you can do with SearchApi

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.

Account, 1 operation

get_accountGet accountGETReturns the credits used, the monthly allowance and the hourly rate limit of the account.

Analytics, 1 operation

get_usage_analyticsGet usage analyticsGETReturns search usage aggregated per day or per hour, broken down by engine.

Location, 1 operation

list_locationsList locationsGETReturns the canonical location names the search endpoint accepts.

Search, 1 operation

list_searchesList searchesGETLists the searches the account ran, with their engine, parameters and timings.

Search result, 1 operation

searchSearchGETRuns a search on the chosen engine and returns its parsed results.

Use SearchApi from Claude Code, Cursor or Codex

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

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

SearchApi integration FAQ

What can you do with the SearchApi integration?

LiveContext exposes 5 operations on SearchApi, covering account, analytics, location and search. Common uses include pulling Google results for a rank tracker, finding which engine drives the credit spend and checking the remaining credits before a large crawl.