SerpResult integration
SerpResult runs live web searches on Google, Bing, DuckDuckGo, Yahoo, Brave or Yandex from any of 193 countries and returns the organic results (position, title, url, domain, snippet) as JSON. Run one search, run up to 50 searches in one request, or read the account's plan and remaining credits. Each search costs 1 credit, a cached answer included; reading the account is free. The dashboard's usage history, billing and API key management routes accept only a browser session and are not offered. Authentication is a SerpResult secret key (sk_live_ or sk_test_; a test key still spends real credits) sent as a Bearer token; create it in the SerpResult dashboard under Developers, API keys.
Say what should happen.
The workflow builds itself.
Common SerpResult use cases
- checking credits before a large batch
- checking rankings for a keyword list in one call
- checking where a site ranks for a keyword in a given country
- testing that a SerpResult key works
- giving an agent fresh web results from Google or Bing
- running the same query on several engines or countries
What you can do with SerpResult
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.
Web search result, 2 operations
bulk_searchBulk searchPOSTAgents: ask firstRuns 1 to 50 searches in one request and returns one row per query, in input order: status ok with that search's organic results, or status error with a code. Each row that reaches the engine costs 1 credit.searchSearchGETAgents: ask firstRuns one live search on the chosen engine and country and returns its organic results in rank order (position, title, url, domain, snippet). Costs 1 credit, a cached answer included; an empty results.organic is not an error.
Account, 1 operation
get_accountGet accountGETAgents: ask firstReturns the account behind the key: its email, plan (trial, starter, growth, business or enterprise), credits_available (remaining quota plus credit-pack balance) and the key's id, label and mode. Costs no credit.
Use SerpResult from Claude Code, Cursor or Codex
Connect SerpResult in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its SerpResult operations become tools the client can call, next to every other integration you connected.
claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"
[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"{
"mcpServers": {
"livecontext": {
"type": "http",
"url": "https://livecontext.ai/mcp",
"headers": {
"X-API-Key": "YOUR_API_KEY"
}
}
}
}How to connect SerpResult
- Create your workspace
Sign up free. Nothing to install.
- Connect SerpResult once
Add your SerpResult 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.
SerpResult integration FAQ
What can you do with the SerpResult integration?
LiveContext exposes 3 operations on SerpResult, covering web search result and account. Common uses include checking credits before a large batch, checking rankings for a keyword list in one call and checking where a site ranks for a keyword in a given country.
