MCP / Web research

Firecrawl MCP

Firecrawl web scraping to clean agent-ready data: scrape a page to markdown or JSON, crawl a site, map its urls, search the web. Connect it to Claude, Codex, Cursor or any MCP client through one FlyMy.AI MCP.

Ready to use: no key13 actionsWeb research
Ask your agent
Read https://example.com and return its main content as Markdown.

Paste it into an assistant connected to FlyMy.AI. The agent picks the actions.

What Firecrawl MCP can do

13 actions in the FlyMy.AI catalog, the most used first. Your agent finds them through search_tools and calls the one the task needs.

ActionWhat it does
firecrawl_scrapeScrape one page and return its content Pick formats (markdown, html, links, summary, screenshot, or a json object with a prompt/schema).
firecrawl_get_extract_statusCheck an extract job and fetch the structured result
firecrawl_extractStart extracting structured data from pages Give urls (wildcards allowed) plus a prompt and/or schema describing the output; optional enable_web_search.
firecrawl_batch_scrapeStart a batch scrape of many URLs in one job Give urls plus optional formats, only_main_content, include_tags, exclude_tags.
firecrawl_cancel_crawlCancel a running crawl job WRITE action
firecrawl_crawlStart crawling a whole site. Returns {id} to poll with firecrawl_get_crawl_status.
firecrawl_crawl_params_previewPreview the crawl parameters Firecrawl would derive from a prompt without running a crawl with url + prompt.
firecrawl_get_batch_scrape_statusCheck a batch scrape job and fetch results so far
firecrawl_get_crawl_statusCheck a crawl job and fetch results so far.
firecrawl_get_credit_usageGet remaining credits for the team
firecrawl_get_token_usageGet remaining tokens and plan / billing period for the team
firecrawl_mapMap a site into a list of URLs quickly
Show all 13 actions
ActionWhat it does
firecrawl_searchSearch the web and optionally scrape each result Pass a query plus optional limit, sources (web/news/images), location, tbs (time filter), and scrape_options (set to also return full page content).

Ask your agent

Requests to paste as they are. Each one runs on the actions named under it.

“Read https://example.com and return its main content as Markdown.”uses firecrawl_scrape
“Map my documentation site and list URLs whose paths mention webhooks.”uses firecrawl_map
“Preview the crawl settings for collecting only the product pages of this site, with a limit of 20 pages.”uses firecrawl_crawl_params_preview

Connect Firecrawl in a minute

One MCP for every integration. Add it once, then every MCP in the catalog is a request away.

  1. 01

    Add FlyMy.AI

    Add the FlyMy.AI MCP to your assistant with one of the commands below and sign in. No key to copy.

  2. 02

    Nothing to connect

    Firecrawl runs on the FlyMy.AI platform key: no account and no key of yours. Calls are billed to your FlyMy.AI balance.

  3. 03

    Ask

    Paste a request from this page. Every run shows what it cost.

Claude Code
claude mcp add --transport http flymyai https://mcp-agents.flymy.ai/mcp

Then run /mcp in Claude Code and sign in.

Codex
codex mcp add flymy --url https://mcp-agents.flymy.ai/mcp

Then run codex mcp login flymy to sign in.

claude.ai and Claude Desktop
https://mcp-agents.flymy.ai/mcp

Settings, Connectors, Add custom connector: paste this URL.

Pay per run

Calls run on FlyMy.AI's key and are billed per call to your FlyMy.AI balance at the published rate. No seats and no minimum.

Go to the source

From the FlyMy.AI platform catalog of 2026-10-31: name, description, actions and setup as the platform lists them. Examples are requests to paste, not recorded runs.