Does it handle JavaScript?

Yes — Firecrawl renders JS server-side and returns the post-rendered DOM.

How do I extract structured data?

The `extract` tool takes a schema (Zod-style or JSON Schema) and an LLM does the extraction. Useful for pulling fields out of listings.

Yes — set `FIRECRAWL_API_URL` to your own Firecrawl deployment.

Firecrawl

Name: Top MCPs — curated MCP directory
Creator: Top MCPs
License: https://creativecommons.org/licenses/by/4.0/

Official

Scrape, crawl, extract structured data, and search the web from an AI agent.

Score 91(?)FirecrawlMIT 7.3kVerified Aug 19, 2026Top MCPs for Web Scraping →

Install View on GitHub

Quick answer

What it does

Exposes Firecrawl operations as MCP tools: single-page scrape, depth-limited crawl, schema-driven extract, and web search with content fetching.

Best for

JS-rendered page scraping
Multi-page crawls (docs sites)
Schema-driven structured extraction
Web search with content body

Not for

Sites with an existing API
Volumes that exceed Firecrawl's rate limits

Source: top-mcps.com/mcp/firecrawl — verified Aug 2026

Setup recipe

Pick your client, then follow the three steps.

Install

claude_desktop_config.jsonjson

{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "${FIRECRAWL_API_KEY}",
        "FIRECRAWL_API_URL": "${FIRECRAWL_API_URL}"
      }
    }
  }
}

Paste under mcpServers. Fully quit and reopen Claude after editing.

CLI or .mcp.jsonshell

# export FIRECRAWL_API_KEY=fc-your_key
# export FIRECRAWL_API_URL=https://api.firecrawl.dev
claude mcp add firecrawl -- npx -y firecrawl-mcp

Run from your repo. Commit .mcp.json to share with your team.

.cursor/mcp.jsonjson

{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "${FIRECRAWL_API_KEY}",
        "FIRECRAWL_API_URL": "${FIRECRAWL_API_URL}"
      }
    }
  }
}

Global path: ~/.cursor/mcp.json. Reload window after editing.

.vscode/mcp.jsonjsonc

{
  "servers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "${FIRECRAWL_API_KEY}",
        "FIRECRAWL_API_URL": "${FIRECRAWL_API_URL}"
      }
    }
  }
}

VS Code uses the "servers" key (not "mcpServers").

~/.codeium/windsurf/mcp_config.jsonjson

{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "${FIRECRAWL_API_KEY}",
        "FIRECRAWL_API_URL": "${FIRECRAWL_API_URL}"
      }
    }
  }
}

Open via Cascade → hammer icon → Configure.

cline_mcp_settings.jsonjson

{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": [
        "-y",
        "firecrawl-mcp"
      ],
      "env": {
        "FIRECRAWL_API_KEY": "${FIRECRAWL_API_KEY}",
        "FIRECRAWL_API_URL": "${FIRECRAWL_API_URL}"
      }
    }
  }
}

Open via the Cline sidebar → MCP Servers → Edit.

~/.continue/config.jsonjson

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "npx",
          "args": [
            "-y",
            "firecrawl-mcp"
          ],
          "env": {
            "FIRECRAWL_API_KEY": "${FIRECRAWL_API_KEY}",
            "FIRECRAWL_API_URL": "${FIRECRAWL_API_URL}"
          }
        }
      }
    ]
  }
}

Continue uses modelContextProtocolServers with a transport block.

~/.codex/config.tomlshell

# ~/.codex/config.toml
[mcp_servers.firecrawl]
command = "npx"
args = [
  "-y",
  "firecrawl-mcp",
]
env = { FIRECRAWL_API_KEY = "${FIRECRAWL_API_KEY}", FIRECRAWL_API_URL = "${FIRECRAWL_API_URL}" }

Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.

~/.config/zed/settings.jsonjsonc

{
  "context_servers": {
    "firecrawl": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "firecrawl-mcp"
        ]
      },
      "env": {
        "FIRECRAWL_API_KEY": "${FIRECRAWL_API_KEY}",
        "FIRECRAWL_API_URL": "${FIRECRAWL_API_URL}"
      }
    }
  }
}

Zed calls them "context_servers". Settings live-reload on save.

ChatGPT → Apps directorynone

Firecrawl doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build.

2
Set required secrets
Set FIRECRAWL_API_KEY, FIRECRAWL_API_URL in your shell environment before launching your MCP client.
3
Try a minimum working prompt
Minimum working prompt pending verification. Try any prompt from the MCP’s README once installed.

Tools & permissions

Tool	Description	Args	Side effects
`firecrawl_scrape`	Scrape content from a single URL with advanced options. Best for single-page extraction when you know which page holds the information.	url: string	Network
`firecrawl_map`	Map a website to discover all indexed URLs, for finding sections or deciding what to scrape next.	url: string	Network
`firecrawl_crawl`	Start a crawl job, poll until it reaches a terminal state, and return the final crawl status and data.	url: string	Network
`firecrawl_check_crawl_status`	Check the status and results of an existing crawl job by ID.	id: string	Read
`firecrawl_search`	Search the web and return result snippets; a research profile narrows results to research-affiliated sites.	query: string	Network
`firecrawl_parse`	Parse local files or hosted uploads — PDFs, Word documents, spreadsheets, and HTML — via the parse endpoint.	—	Network
`firecrawl_monitor_list`	List configured change monitors.	—	Read
`firecrawl_monitor_run`	Trigger a monitor check immediately rather than waiting for its schedule.	—	Network
`firecrawl_monitor_delete`	Delete a monitor. Destructive — only call when the user intends to remove it.	—	Write

Agent prompt pack

— copy into Claude, Cursor, or ChatGPT.

Paste into Claude, Cursor, or ChatGPT. Edit the [brackets] before sending.

Recommend the best MCP servers for [task: e.g. web scraping work] in [client: Claude].

Constraints:
- Prefer tools that are [official | open-source | read-only] — pick what matters for my use case.
- Exclude MCPs that require [e.g. a paid plan, OAuth-only flows, remote-only transport].
- Return at most 3 picks, ranked.

For each pick include:
1. One-sentence rationale.
2. The ready-to-paste install snippet for my client.
3. Any required secrets I need to create before installing.

Cross-check the top-mcps.com listing: https://top-mcps.com/top-mcps-for-web-scraping

Compare Firecrawl against a real alternative. Swap the second MCP in [brackets] if you want a different match.

Compare Firecrawl MCP vs [Fetch MCP] for the following job: [describe the job, e.g. "let an agent create GitHub issues on bug triage"].

Judge them on:
- Setup time and complexity (what a new user hits first).
- Auth model (none / API key / OAuth 2.1) and credential risk.
- Transport (stdio / Streamable HTTP / SSE) and where the server runs.
- Required secrets and the blast radius if they leak.
- Operational risk in an unattended agent loop.
- Which one is "good enough" for a weekend prototype vs. production.

End with one sentence: which should I pick for my scenario, which is: [my scenario].

References:
- https://top-mcps.com/mcp/firecrawl
- top-mcps.com listing for Fetch

Asks the agent to install and verify. Works inside Claude Code, Cursor Agent, Codex CLI.

Install the Firecrawl MCP server for my [client: Claude] at the default config path for that client.

Use the exact install snippet published at https://top-mcps.com/mcp/firecrawl (fetch https://top-mcps.com/mcp/firecrawl.json for the canonical server.json if you can read URLs).

Before finishing:
1. Create the required secrets (FIRECRAWL_API_KEY, FIRECRAWL_API_URL) and put them in the appropriate env block — do not hard-code them.
2. Restart or reload the client so it picks up the new server.
3. Verify the server is connected (green / running state) and at least one tool is listed.
4. If anything fails, read the client's MCP logs and report the exact error — do not silently retry.

Confirm when done and list the tools the server now exposes.

Frequently asked questions

What changed

— 3 updates tracked.

Sep 26, 2025
v3.2.1 released
Sep 16, 2025
v3.2.0 released
Sep 11, 2025
v3.0.0 released

At a glance

Maintainer: Firecrawl
Transport: stdioStreamable HTTPSSE
Auth model: API key
Required secrets: FIRECRAWL_API_KEYFIRECRAWL_API_URL
Supported clients: ChatGPT
Claude Desktop
Claude Code
Cursor
VS Code
Windsurf
Cline
Continue
Zed
Codex CLI
License: MIT
Language: JavaScript
Latest version: latest
Last verified: Aug 19, 2026

GitHub repo

Rank badge

Maintainer of Firecrawl? Embed the live badge — it re-renders with the current rank and score on every catalog refresh.

[![Ranked #2 in Web Search on Top-MCPs](https://top-mcps.com/badge/firecrawl.svg)](https://top-mcps.com/mcp/firecrawl)

Alternatives

Fetch →
Retrieve web pages and convert them to clean markdown.
Playwright →
Official Microsoft browser automation across Chromium, Firefox, and WebKit.
Browserbase →
Hosted, isolated Chromium runtime for AI agents that need a fresh browser per task.
Puppeteer →
Full browser automation: navigate, click, screenshot, and scrape.
AgentQL →
Query webpages with structured natural language — selectors written for you.

Related guides

Best MCP Servers for Research in 2026 (Search, Scrape, Synthesize) →
Setup Guide

More Web Scraping MCPs

Other tools in the same category worth evaluating.

Fetch

Retrieve web pages and convert them to clean markdown.

webfetchmarkdownscraping

1 minLow

Puppeteer

Full browser automation: navigate, click, screenshot, and scrape.

browserautomationscrapingpuppeteer

5 minMedium

Playwright

Official

Official Microsoft browser automation across Chromium, Firefox, and WebKit.

browserautomationplaywrighttesting

5 minMedium

Compared with Firecrawl

Side-by-side breakdowns for the choices people most often weigh against this MCP.

FirecrawlvsFetch FirecrawlvsAgentQL FirecrawlvsPlaywright FirecrawlvsBrowserbase

Exploring Top MCPs for Web Scraping? See all Web Scraping MCPs →