Integration

SERPHouse integration

SERPHouse is a real-time search engine results (SERP) API for Google, Bing and Yahoo. Run a live web, news or image search on any supported Google, Bing or Yahoo domain, targeted by language, location and device, and search Google Jobs listings. Helper tools list the supported domains, languages and locations, and show the account's plans and remaining credits. Every successful search spends credits. The live search endpoint is marked deprecated by SERPHouse but still answers. Not exposed: the engine-specific search endpoints (Google web, images, news, videos, shopping, local, forums, autocomplete, place details, 100-result search; Bing and Yahoo web, images, news), the batch scheduling and task result routes, the Markdown and HTML response variants and the web page Scraper API. Authentication is the account API key sent as a Bearer token in the Authorization header.

Connect SERPHouse How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in SERPHouse.Built from the 6 SERPHouse tools below, on the connection you add once.

What you can do with SERPHouse

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.

List, 2 operations

list_domainsList domainsGETLists every search engine domain SERPHouse supports (google.com, google.co.uk, bing.com, us.yahoo.com and more). Pass one as the domain of a search.
list_languagesList languagesGETLists the language codes supported for one search engine, as a map of code to language name. Pass a code as lang in a search of that engine.

Google jobs api, 1 operation

google_jobs_searchGoogle jobs searchPOSTSearches Google Jobs and returns job listings with title, company, location, posting details and where to apply.

Info, 1 operation

get_account_infoGet account infoGETReturns the account email and name and each plan with its type, price and credits (available and total). Use it to check the remaining credits before large searches.

Live, 1 operation

search_serp_liveSearch serp liveGETRuns one live Google, Bing or Yahoo search (web, news or image, by domain and serp_type) and returns the parsed page: organic results, people also ask, related searches. Deprecated by SERPHouse but still answering.

Search, 1 operation

search_locationsSearch locationsGETSearches the location database of Google or Bing by name. Each match has an id (pass as loc_id) and a full loc string (pass as loc) for searches.

Use SERPHouse from Claude Code, Cursor or Codex

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

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