Integration

cloro integration

cloro scrapes what AI assistants and Google show for a prompt or query and returns it as structured JSON: the answer text, cited sources, brand entities, shopping cards, places and ads from ChatGPT, Gemini, Microsoft Copilot, Perplexity and Google AI Mode, and organic results, People Also Ask, AI Overview and news from Google Search and Google News, geo-targeted by country. Run a scrape and wait for it, or queue async tasks (one or up to 500 at once, optionally delivered to a webhook) and read them later; also resolve Google redirect links, open a Google product panel, list supported countries and US states, and read the credit balance and queue. Every scrape spends credits (a sync scrape costs 2 more than the same async task; failed requests are free). Authentication is a cloro API key sent as a Bearer token; create it in the cloro dashboard under API keys.

Connect cloro How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

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

Common cloro use cases

dropping a backlog of queued scrapes
reading the result of a queued scrape
queuing a scrape with webhook delivery
checking credits before queuing a large batch
checking a country is supported before a scrape
finding the state code for state-level targeting
getting the real URL behind a Google result link
monitoring news coverage of a brand in a country
checking whether queued scrapes are still waiting
tracking how Google AI Mode answers about a brand

What you can do with cloro

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.

Async task, 3 operations

create_async_taskCreate async taskPOSTAgents: ask firstQueues one scrape (any provider) and returns its task id at once; read the result with get_async_task, or pass webhook_url to have it delivered. No sync surcharge; charged only when the task completes.
create_async_tasks_batchCreate async tasks batchPOSTAgents: ask firstQueues up to 500 scrapes in one request; each task is validated on its own, so one invalid task does not block the rest. Returns per-task results in input order with each task id for get_async_task.
get_async_taskGet async taskGETAgents: ask firstReturns an async task's status (QUEUED, PROCESSING, COMPLETED or FAILED), its credits and, once COMPLETED or FAILED, response: the provider's result or the error. Call again until the status is COMPLETED or FAILED.

Async queue, 2 operations

clear_async_queueClear async queueDELETEAgents: ask firstDeletes every async task still QUEUED for the organization (irreversible) and returns how many were removed. PROCESSING, COMPLETED and FAILED tasks are untouched; queued tasks were never charged.
get_async_queue_statusGet async queue statusGETAgents: ask firstReturns the organization's async queue: tasks queued and processing, queued counts per priority, and concurrency slots used out of the plan's maximum.

Ai mode answer, 1 operation

monitor_google_ai_modeMonitor google ai modePOSTAgents: ask firstSends one prompt to Google AI Mode and returns its answer as structured data: text, sources, shopping cards, inline products, places, ads. Send country or gl. Costs 6 credits (4 base + 2 sync).

Chatgpt answer, 1 operation

monitor_chatgptMonitor chatgptPOSTAgents: ask firstSends one prompt to ChatGPT (web search forced on by default) and returns its answer as structured data: text, sources, citation pills, brand entities, map entries, follow-up form. Costs 7 credits (5 base + 2 sync), more with add-ons.

Copilot answer, 1 operation

monitor_copilotMonitor copilotPOSTAgents: ask firstSends one prompt to Microsoft Copilot and returns its answer as structured data (text, sources, search queries, shopping cards, map entries). Costs 7 credits (5 base + 2 sync); state adds +2.

Country, 1 operation

list_countriesList countriesGETAgents: ask firstReturns the uppercase ISO 3166-1 alpha-2 country codes cloro supports, all of them or only those a given provider supports (model). Free.

Credit balance, 1 operation

get_creditsGet creditsGETAgents: ask firstReturns the organization's remaining credits, credits granted per billing cycle and when the cycle resets (null on the free tier). The balance can lag by up to 60 seconds.

Gemini answer, 1 operation

monitor_geminiMonitor geminiPOSTAgents: ask firstSends one prompt to Google Gemini and returns its answer as structured data (text, sources, places, shopping cards). Costs 6 credits (4 base + 2 sync); state adds +2.

Google news article, 1 operation

monitor_google_newsMonitor google newsPOSTAgents: ask firstRuns one Google News search and returns articles with title, link, snippet, source, date and thumbnail. Send country or gl. Costs 5 credits (3 base + 2 sync); each extra page adds +2.

Google product, 1 operation

get_google_productGet google productPOSTAgents: ask firstOpens the Google product panel behind a productResultToken from monitor_google_search or monitor_google_ai_mode: merchant offers, description, specifications, reviews, images, related products. Costs 3 credits (1 + 2 sync), on success only.

Google redirect link, 1 operation

resolve_google_redirect_linkResolve google redirect linkPOSTAgents: ask firstResolves one Google redirect link (the redirectLink beside a link in monitor_google_search, monitor_google_news or monitor_google_ai_mode results) to its destination URL. Costs 1 credit, only when it resolves.

Google search result, 1 operation

monitor_google_searchMonitor google searchPOSTAgents: ask firstRuns one Google Search and returns organic results, People Also Ask, related searches, ads and shopping cards, optionally the AI Overview. Send query with country (or gl), or a full Google url. Costs 5 credits (3 base + 2 sync), more with add-ons.

Perplexity answer, 1 operation

monitor_perplexityMonitor perplexityPOSTAgents: ask firstSends one prompt to Perplexity and returns its answer as structured data (text, sources, search queries, shopping cards, places). Costs 6 credits (4 base + 2 sync); state adds +2.

Us state, 1 operation

list_statesList statesGETAgents: ask firstReturns the US states (USPS code and name, 50 states plus DC) usable as state on monitor_chatgpt, monitor_gemini, monitor_copilot and monitor_perplexity. Only country US returns states.

Use cloro from Claude Code, Cursor or Codex

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

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

cloro integration FAQ

What can you do with the cloro integration?

LiveContext exposes 17 operations on cloro, covering async task, async queue, ai mode answer and chatgpt answer. Common uses include dropping a backlog of queued scrapes, reading the result of a queued scrape and queuing a scrape with webhook delivery.