Integration

DataFuel integration

DataFuel turns web pages into LLM-ready data. An agent can start a scrape of one URL or a crawl of a whole site (depth and page limit), optionally with an AI prompt and a JSON schema for structured extraction, then read the results (markdown, AI answer and a signed link to the full result) by job, list its jobs, check the API key, and subscribe or unsubscribe a webhook URL. Scrapes and crawls run in the background: start_scrape and start_crawl return a job_id at once. Billing is in credits: 1 per scraped URL, 15 per URL with AI extraction. The scrape-with-login route is not exposed (it takes a site password as a plain parameter). Authentication is a DataFuel API key sent as a Bearer token.

Connect DataFuel How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in DataFuel.Built from the 7 DataFuel tools below, on the connection you add once.

What you can do with DataFuel

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.

Webhook, 2 operations

subscribe_webhookSubscribe webhookPOSTRegisters a URL to receive DataFuel webhook notifications for this account. DataFuel's docs do not describe the payload or any signing secret, so deliveries cannot be verified.
unsubscribe_webhookUnsubscribe webhookDELETEStops webhook notifications to a URL registered with subscribe_webhook.

Api key, 1 operation

get_api_key_infoGet api key infoGETReturns the DataFuel user id that owns the API key and whether the key is valid. Use it to test a connection.

Crawl job, 1 operation

start_crawlStart crawlPOSTStarts a crawl from a base URL and returns its job_id at once; each crawled page becomes one scrape in list_scrapes (job_id). Bills 1 credit per page, 15 with AI extraction; limit caps the pages.

Job, 1 operation

list_jobsList jobsGETLists the ids of every scrape and crawl job created with this API key. Pass an id to list_scrapes (job_id) to read its results.

Scrape, 1 operation

list_scrapesList scrapesGETLists scrape results, most recent first: URL, status, job status and a signed link to the full result. Filter by job_id (from start_scrape or start_crawl) or url; set markdown or ai_response to get the content inline.

Scrape job, 1 operation

start_scrapeStart scrapePOSTStarts a scrape of one URL and returns its job_id at once. Read the result with list_scrapes (job_id, markdown=true) until job_status is finished. 1 credit, or 15 with ai_prompt or json_schema.

Use DataFuel from Claude Code, Cursor or Codex

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

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