How to Set Up Firecrawl MCP in Claude Code and Cursor

November 5, 2026

Firecrawl MCP is the official Model Context Protocol server for Firecrawl, the web scraping service. It exposes four main tools — scrape a URL, crawl a site, search the web, and extract structured data — so an agent can pull live web content without you writing fetch code.

Setup is one API key and one JSON block. The annoying part is choosing tools carefully, because an over-broad tool set makes agents slow and expensive.

What does the Firecrawl MCP server actually expose?

Four tools that cover most research needs:

  • firecrawl_scrape — fetch one URL and return Markdown, HTML or plain text
  • firecrawl_crawl — start a job that walks a site up to a page limit and returns each page as Markdown
  • firecrawl_search — web search that can optionally scrape the top results
  • firecrawl_extract — pull structured fields from pages using a prompt and a JSON schema

Responses are Markdown by default, which is the format LLMs handle best. That default alone saves you an HTML-stripping step in most pipelines.

How do you get a Firecrawl API key?

Create an account at firecrawl.dev, open the dashboard, and copy the key with the fc- prefix. The free tier gives you a few hundred credits to test; paid plans start around $16/month for Small. One page scrape generally costs 1 credit, and crawling a 50-page site costs roughly 50.

Keep the key out of your shell history. Put it in an environment variable and reference that variable from the MCP config, not the literal string.

How do you add it to Claude Code?

The CLI path is the simplest:

claude mcp add firecrawl -e FIRECRAWL_API_KEY=fc-your-key -- npx -y firecrawl-mcp

Then start Claude Code and run /mcp to confirm the server shows as connected and lists four tools. If it shows nothing, the usual cause is a broken npx cache — run npx -y firecrawl-mcp manually once to populate it.

For project-scoped setup, add the same entry under mcpServers in .mcp.json at the repo root. Use that when a teammate should get the server automatically.

How do you add it to Cursor and other clients?

In Firecrawl MCP the pattern is the same for every JSON-configured client. Open the MCP settings file (~/.cursor/mcp.json for Cursor) and add:

{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": ["-y", "firecrawl-mcp"],
      "env": { "FIRECRAWL_API_KEY": "fc-your-key" }
    }
  }
}

Restart the client. Cursor shows a green dot next to the server name when it started. VS Code with Copilot uses the same shape in .vscode/mcp.json.

Which tools should you enable by hand?

All four, and agents get chatty. In my test, an agent asked to “compare three competitors’ pricing” opened with a crawl of each homepage instead of a search, which burned about 400 credits on pages nobody read.

Two mitigations:

  1. Disable firecrawl_crawl for research-heavy projects and keep only scrape, search and extract.
  2. In your agent instructions, add: “Use search before crawl. Never crawl more than 10 pages without asking.”

Credits are the real constraint. An agent with a crawl tool and no instruction will exhaust a free tier in one session.

What breaks most often?

  • Node version. The server needs Node 18 or newer. Node 16 produces a silent start failure that looks like a config error.
  • Rate limits. Free-tier accounts hit per-minute limits during crawls, and the agent reports the error as “empty content”.
  • JavaScript-heavy sites. Default scraping misses content rendered on the client. Pass the wait-for parameter so the page has time to settle.
  • Auth walls. Firecrawl cannot log in for you. Paywalled content returns a login page, not the article.

Who is this for

Good fit: agents that need current web data — competitor research, docs checking, pricing comparison. Poor fit: anything where the source must be stable over time, since scraped pages change. If you need repeatable input, cache the Markdown you scraped instead of re-running the tool.

Quick Summary

  • Firecrawl MCP is the official MCP server exposing scrape, crawl, search and extract tools.
  • Get an fc- API key at firecrawl.dev; free tier gives a few hundred test credits, paid from ~$16/month.
  • Install with claude mcp add firecrawl -e FIRECRAWL_API_KEY=... -- npx -y firecrawl-mcp, or a mcpServers block in Cursor.
  • Disable crawl for research work or agents burn 400+ credits per session.
  • Needs Node 18+; paywalled and JS-heavy pages are the common failure cases.