Firecrawl

Firecrawl MCP integration

Scrapes and searches live pages, crawls entire sites, and extracts typed fields from them without anyone copy-pasting HTML.

Connect FirecrawlSee all integrations

29actions available

Three actions you can hand over today

Every action runs live through MCP. Nothing to build, nothing to maintain.

  • Search

    Lyro searches the web for a query and pulls back scraped content from the top results. This means a support agent gets the current answer to a customer's question instantly, without leaving the conversation to browse the web.

  • Start a web crawl

    Lyro launches a full site crawl from a starting URL, following links and extracting content as it goes. That lets a team pull structured documentation from a whole knowledge base at once, instead of copying pages by hand.

  • Generate llms.txt for a website

    Lyro generates an llms.txt file that converts a website's content into a format language models can read directly. That gives a team a ready reference file for AI tools without manually reformatting every page.

See all 29 actions

How businesses use Firecrawl + Lyro

Each card is one request a support team gets, and the Firecrawl actions Lyro runs to close it.

  • Answer from the live page, not a cached summary

    Lyro scrapes the exact URL a customer is asking about, searches the web when it needs a source it does not have, and maps a domain to find the right page first.

    Scrape URLSearchMap Multiple URLs

  • Pull typed fields out of a page

    When a plain text answer is not enough, Lyro starts an extraction job against a schema, polls it to completion, and batches several URLs into one run instead of scraping them one at a time.

    Extract Structured DataGet Extract Job StatusBatch Scrape Multiple URLs

  • Refresh a knowledge source from its own site

    Lyro starts a crawl across a documentation or help site, tracks it to completion, and can generate an LLMs.txt file so the content comes back in a form built for a model to read.

    Start A Web CrawlGet Crawl Job StatusGenerate LLMs.txt For A Website

  • Keep long-running jobs and credits under control

    Lyro lists the crawls already running, cancels one that is no longer needed, reads why individual URLs failed, and checks the team credit balance before starting an expensive run.

    Get All Active Crawl JobsCancel A Crawl JobGet Team Credit Usage

How it works

Get started in 3 steps

Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Firecrawl actions it has and picks the ones a request needs.

  1. 01

    Connect Firecrawl

    Authorize the Firecrawl account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.

  2. 02

    Tell your agent what you need

    Describe the job the way you would hand it to a teammate. Lyro maps it to the Firecrawl actions that close it and chains as many as the request needs.

  3. 03

    Watch it work

    The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.

    Get started free
Firecrawl · Lyro

Everything else about Firecrawl

Setup, permissions, and the limits of what Lyro can do inside Firecrawl.

  • The team behind the API key you connect. The toolkit exposes Get Team Credit Usage and Get Team Token Usage along with their historical monthly variants, so Lyro can read the remaining balance before it starts a large crawl or batch scrape rather than discovering the limit mid-run.

Every action available in Firecrawl

All 29 actions your agent can call on Firecrawl, straight from the live MCP connection.

  • Cancel an agent job

    Cancel an in-progress agent job by its ID.

  • Batch scrape multiple urls

    Scrape multiple URLs in batch with concurrent processing.

  • Cancel a batch scrape job

    Cancel a running batch scrape job using its unique identifier.

  • Get batch scrape status

    Retrieves the current status and results of a batch scrape job using the job ID.

  • Get errors from batch scrape job

    Retrieve error details from a batch scrape job, including failed URLs and URLs blocked by robots.txt.

  • Start a web crawl

    Initiates a Firecrawl web crawl from a given URL, applying various filtering and content extraction rules, and polls until the job is complete; ensure the URL is accessible and any regex patterns for paths are valid.

  • Cancel a crawl job

    Cancels an active or queued web crawl job using its ID; attempting to cancel completed, failed, or previously canceled jobs will not change their state.

  • Cancel a crawl job

    Cancel a running crawl job by its ID.

  • Get crawl job status

    Retrieve the status and results of a Firecrawl crawl job.

  • Get errors from a crawl job

    Retrieve errors from a Firecrawl crawl job.

  • Get all active crawl jobs

    Retrieve all active crawl jobs for the authenticated team.

  • Preview crawl parameters

    Preview crawl parameters before starting a crawl by generating optimal configuration from natural language instructions.

  • Start a web crawl (v2) [new]

    [NEW v2 API] Initiates a Firecrawl v2 web crawl with enhanced features over v1: natural language prompts for automatic crawler configuration, crawlEntireDomain for sibling/parent page discovery, better depth control with maxDiscoveryDepth, subdomain support, and full webhook configuration.

  • Get team credit usage

    Get current team credit usage information.

  • Get historical team credit usage

    Retrieve historical team credit usage on a monthly basis.

  • Extract structured data

    Extracts structured data from web pages by initiating an extraction job and polling for completion; requires a natural language prompt or a JSON schema (one must be provided).

  • Get extract job status

    Retrieve the status and results of a previously submitted extract job.

  • Get agent job status

    Get the status and results of an agent job.

  • Get deep research status

    Retrieves the status and results of a deep research job by its ID.

  • Get the status of a crawl job

    Retrieves the current status, progress, and details of a web crawl job, using the job ID obtained when the crawl was initiated.

  • Generate llms.txt for a website

    Initiates an async job to generate an LLMs.txt file for a website, converting web content into LLM-friendly format.

  • Get llms.txt generation job status

    Get the status and results of an LLMs.txt generation job.

  • Map multiple urls

    Maps a website by discovering URLs from a starting base URL, with options to customize the crawl via search query, subdomain inclusion, sitemap handling, and result limits; search effectiveness is site-dependent.

  • Get team queue status

    Retrieve metrics about the team's scrape queue.

  • Scrape URL

    Scrapes a publicly accessible URL, optionally performing pre-scrape browser actions or extracting structured JSON using an LLM, to retrieve content in specified formats.

  • Search

    Performs a web search for a query, scrapes content from the top search results using Firecrawl, and returns details in specified formats.

  • Start an agent job

    Start an agent job for agentic web extraction with multi-page navigation and interaction capabilities.

  • Get team token usage

    Retrieve the current team's token usage and balance information for Firecrawl's Extract feature.

  • Get historical team token usage

    Retrieve historical team token usage on a monthly basis.

The tools Firecrawl sits next to

Same connection, same setup. Pick the next one your team already uses.

Browse every integration

Ready to connect Firecrawl?

Authorize the account and your agent has all 29 actions from the first conversation.

Connect FirecrawlTalk to sales
Support agent working at a laptop next to the Lyro mascot