Integration

Firecrawl integration

Firecrawl is a web data API for AI applications that converts any website into clean, LLM-ready markdown, HTML, or structured data. It handles JavaScript rendering, anti-bot bypasses, sitemaps, and content extraction. Core capabilities include single-page scraping, multi-page crawling, URL discovery (map), and structured data extraction with schema definitions.

Connect Firecrawl How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Firecrawl.Built from the 10 Firecrawl tools below, on the connection you add once.

Common Firecrawl use cases

poll crawl completion
stop a long-running crawl
poll extraction completion
poll batch scrape completion
scrape a list of product pages
scrape full documentation site
convert webpage to markdown for LLM
extract product data from e-commerce
discover site structure before crawling
research a topic with full page content

What you can do with Firecrawl

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.

Crawl job, 2 operations

cancel_crawlCancel crawlDELETECancel an in-progress crawl job. Already scraped data remains available.
get_crawl_statusGet crawl statusGETGet status and results of an asynchronous crawl job.

Batch scrape, 1 operation

batch_scrapeBatch scrapePOSTScrape multiple URLs in a single batch. Runs asynchronously with status polling.

Batch scrape job, 1 operation

get_batch_scrape_statusGet batch scrape statusGETGet status and results of an asynchronous batch scrape job.

Extract job, 1 operation

get_extract_statusGet extract statusGETGet status and results of an asynchronous extract job.

Structured data, 1 operation

extract_structured_dataExtract structured dataPOSTExtract structured data from URLs using AI and a JSON schema. Supports natural language prompts.

Web search, 1 operation

searchSearchPOSTSearch the web and get full scraped content for each result. Combines search with scraping.

Webpage, 1 operation

scrape_urlScrape urlPOSTScrape a single URL and convert it to clean markdown or HTML. Handles JavaScript and anti-bot protections.

Website, 1 operation

crawl_websiteCrawl websitePOSTCrawl an entire website and return all pages as clean markdown. Runs asynchronously.

Website urls, 1 operation

map_websiteMap websitePOSTDiscover all URLs on a website instantly. Returns links ordered by relevance.

Firecrawl API rate limits

10 requests per minute

Free tier: 10 scrape/min, 1 crawl/min, 5 search/min. Higher tiers increase limits.

These are the limits Firecrawl documents, not ones LiveContext measured. They can change and often depend on your plan, so check the Firecrawl documentation for current values.

Use Firecrawl from Claude Code, Cursor or Codex

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

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

Firecrawl integration FAQ

What can you do with the Firecrawl integration?

LiveContext exposes 10 operations on Firecrawl, covering crawl job, batch scrape, batch scrape job and extract job. Common uses include poll crawl completion, stop a long-running crawl and poll extraction completion.

What are the Firecrawl API rate limits?

Firecrawl documents 10 requests per minute. Free tier: 10 scrape/min, 1 crawl/min, 5 search/min. Higher tiers increase limits. Limits are set by Firecrawl and can depend on your plan.