Integration

AnswerLine integration

AnswerLine returns the live answers people see from ChatGPT, Gemini, Perplexity, Copilot, Grok and Google AI Mode, and Google Search and Google News results, as structured JSON: the answer text, cited sources, citation pills, brands, places and products, organic results, People Also Ask, ads and the AI Overview. An agent can ask an engine synchronously (up to about five minutes), queue async tasks one at a time or in batches of up to 500 and read their results, watch or clear its task queue, list the countries and US states each engine serves, and read the account's USD balance. Each answered request is charged from a prepaid USD balance (new accounts get 100 free requests); failed requests are not charged. Account, key, team and webhook-secret management stay in the AnswerLine dashboard. Authentication is an AnswerLine API key sent as a Bearer token.

Connect AnswerLine How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in AnswerLine.Built from the 17 AnswerLine tools below, on the connection you add once.

What you can do with AnswerLine

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.

Ai answer, 6 operations

get_ai_mode_answerGet ai mode answerPOSTAgents: ask firstAsks Google AI Mode a prompt (up to 2,000 characters), localized by country, city or language, and returns its answer, sources, citation pills, places, shopping and product cards, ads, videos and map points. Charged per answer.
get_chatgpt_answerGet chatgpt answerPOSTAgents: ask firstAsks ChatGPT a prompt (up to 2,000 characters) as asked from a chosen country and returns its answer text, cited sources, citation pills, entities, places, products and images. Charged per answer; waits up to about five minutes.
get_copilot_answerGet copilot answerPOSTAgents: ask firstAsks Microsoft Copilot a prompt (up to 2,000 characters) as asked from a chosen country and returns its Bing-grounded answer text, cited sources, citation pills, shopping cards, places and the web searches it ran. Charged per answer.
get_gemini_answerGet gemini answerPOSTAgents: ask firstAsks Google Gemini a prompt (up to 2,000 characters) as asked from a chosen country, optionally a US state, and returns its grounded answer, cited sources, citation pills, places, product and entity cards. Charged per answer.
get_grok_answerGet grok answerPOSTAgents: ask firstAsks Grok a prompt (up to 2,000 characters) as asked from a chosen country and returns its answer text, cited sources (X posts included), the searches it ran and its suggested follow-up questions. Charged per answer.
get_perplexity_answerGet perplexity answerPOSTAgents: ask firstAsks Perplexity a prompt (up to 2,000 characters) as asked from a chosen country and returns its answer text, cited sources, citation pills, related queries, images, videos, places, hotels and shopping cards. Charged per answer.

Task, 3 operations

create_taskCreate taskPOSTAgents: ask firstQueues one engine request as a background task and returns its id at once; read the result with get_task, or pass webhook to have it POSTed when done. Charged when it completes (failed or cleared tasks are free).
create_tasks_batchCreate tasks batchPOSTAgents: ask firstQueues 1 to 500 engine requests in one call; each is validated and admitted on its own, and results lists each by its index (task id, or the error). Read results with get_task. Charged per completed task.
get_taskGet taskGETAgents: ask firstReturns an async task's status (QUEUED, PROCESSING, COMPLETED or FAILED), its charge, and once finished the engine's result or the error in response. Only COMPLETED and FAILED are final; call again while it runs.

Queue, 2 operations

clear_queueClear queueDELETEAgents: ask firstDeletes all of the organization's tasks still QUEUED (running, completed and failed tasks stay). Their held amounts are released, nothing is charged. Answers cleared (count), or clearing true when a long queue is still being emptied.
get_queue_statusGet queue statusGETAgents: ask firstReturns the organization's async queue right now: tasks queued and processing, queued tasks per priority, and the concurrency in use.

Balance, 1 operation

get_balanceGet balanceGETAgents: ask firstReturns the USD amount the account can still spend: its balance less what open tasks hold back. perCycle and cycleResetsAt are always null (balances do not reset).

Country, 1 operation

list_countriesList countriesGETAgents: ask firstLists the ISO 3166-1 alpha-2 country codes AnswerLine serves, all of them or those of one engine (model). A country missing from an engine's list is refused with a 400 on that engine.

News article, 1 operation

search_google_newsSearch google newsPOSTAgents: ask firstRuns a Google News search for a query in one of the 71 countries with a Google News edition and returns the articles: title, link, source and date for each. Charged per search; waits up to about five minutes.

Redirect link, 1 operation

resolve_google_redirectResolve google redirectPOSTAgents: ask firstReturns the destination URL of one Google redirect link (the redirectLink next to a resolved link in search_google, get_ai_mode_answer or search_google_news results). Free; Google is given up to 10 seconds to answer.

Search result, 1 operation

search_googleSearch googlePOSTAgents: ask firstRuns a Google web search (query plus country, or a full Google search URL) and returns organic results, People Also Ask, ads, local pack, knowledge graph, related searches and, on request, the AI Overview. Charged per search.

State, 1 operation

list_statesList statesGETAgents: ask firstLists the US state codes for state-level targeting (the state field, served on Gemini only). Only country US returns states; any other country gives an empty list. DC is listed but fails, uncharged.

Use AnswerLine from Claude Code, Cursor or Codex

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

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