electrical_services

Firecrawl MCP Server — Hosted Web Search Integration

MCP Server language Hosted language Public

Scrape web pages, crawl entire sites, extract structured data, and search the web — AI-native web data extraction for RAG pipelines.

@aerostack verified

• v0.1.0 • MIT • Updated Jun 28, 2026

add_circleAdd to Workspace

robot_2

Use with AI AssistantsMCP

Connect Claude, Cursor, or any MCP-compatible client — then call tools directly

① Add This MCP Server

Paste into your AI client config — then all its tools are available instantly.

.claude/mcp.json

{
  "mcpServers": {
    "firecrawl": {
      "url": "https://mcp.aerostack.dev/s/aerostack/mcp-firecrawl",
      "headers": {
        "Authorization": "Bearer YOUR_AEROSTACK_TOKEN"
      }
    }
  }
}

Replace YOUR_AEROSTACK_TOKEN with your API token from the dashboard.

② Call a Tool

Ask your AI assistant to call a specific tool, or send raw JSON-RPC:

+1 more

Natural Language Prompt

“Use the _ping tool to verify firecrawl api connectivity and credits balance. used internally by aerostack to validate credentials”

Using a Workspace?

Add this MCP to your Workspace — your team shares one token, secrets are stored securely, and every AI agent in the workspace can call it without per-user setup.

add_circleAdd to Workspace

description Overview

mcp-firecrawl — Firecrawl Web Scraping MCP Server

Scrape web pages, crawl entire sites, extract structured data, and search the web — AI-native web data extraction for RAG pipelines.

Give your AI agents the ability to read any web page. Scrape JavaScript-rendered pages to clean markdown, crawl entire sites with depth control, extract structured data with natural language prompts, discover all URLs on a domain, and search the web with scraped results — perfect for RAG, research, and data pipelines.

Live endpoint: https://mcp.aerostack.dev/s/aerostack/mcp-firecrawl

What You Can Do

Scrape any web page to clean markdown (handles JS-rendered content)
Crawl entire websites with configurable depth and path filters
Extract structured data using natural language or JSON schema
Map all URLs on a website (sitemap discovery)
Search the web and get scraped content from top results
Get page metadata, links, and optional screenshots

Available Tools

Tool	Description
`_ping`	Verify Firecrawl API connectivity
`scrape`	Scrape a page to markdown/HTML with JS rendering support
`crawl`	Start an async crawl of an entire site (returns job ID)
`crawl_status`	Check crawl progress and retrieve results
`map`	Discover all URLs on a website without scraping
`extract`	Extract structured data using prompts or JSON schema
`search`	Search the web and return scraped content from results

Configuration

Variable	Required	Description	How to Get
`FIRECRAWL_API_KEY`	Yes	Firecrawl API Key	firecrawl.dev → Sign up → Dashboard → API Keys → Copy key

Free tier: 500 credits/month. Each scrape = 1 credit, crawl = 1 credit per page. See firecrawl.dev/pricing for details.

Quick Start

Add to Aerostack Workspace

Go to aerostack.dev → Your Project → MCPs
Search for "Firecrawl" and click Add to Workspace
Add FIRECRAWL_API_KEY under Project → Secrets

Example Prompts

"Scrape the Hacker News front page and summarize the top stories"
"Crawl docs.example.com up to depth 3 and include only /api/* paths"
"Extract all product names and prices from this product listing page"
"Map all URLs on stripe.com/docs"
"Search the web for 'best practices for RAG pipelines 2026' and summarize"

Direct API Call

curl -X POST https://mcp.aerostack.dev/s/aerostack/mcp-firecrawl \
  -H 'Content-Type: application/json' \
  -H 'X-Mcp-Secret-FIRECRAWL-API-KEY: fc-xxxxxxxxxxxx' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"scrape","arguments":{"url":"https://example.com"}}}'

Security Notes

Firecrawl API keys are injected at the Aerostack gateway layer — never stored in the worker
HTML content is truncated to 50KB to prevent oversized responses
Crawl results are async — start with crawl then poll with crawl_status
Firecrawl handles robots.txt and rate limiting on the target sites

License

MIT

terminal Tools (7)

Available tools on this MCP server. Each tool can be called directly from any AI agent.

terminal

_ping #1

Verify Firecrawl API connectivity and credits balance. Used internally by Aerostack to validate credentials.

terminal

scrape #2

Scrape a single web page and return clean markdown content, metadata, links, and optionally a screenshot. Handles JavaScript-rendered pages.

terminal

crawl #3

Start an async crawl of an entire website from a starting URL. Returns a job ID to check progress. Follows links up to a configurable depth.

terminal

crawl_status #4

Check the status of an async crawl job and retrieve results when complete

terminal

map #5

Discover all URLs on a website without scraping content — returns a sitemap-like list of all pages found

terminal

extract #6

Extract structured data from a web page using a natural language prompt or JSON schema. Returns clean, typed data.

terminal

search #7

Search the web using Firecrawl and return scraped content from the top results — combines search + scrape in one call

Details

upgrade Version 0.1.0

gavel License MIT

wifi Transport streamable-http

lock Access Public

category Category Web Search

terminal Tools 7

language Live Endpoint

https://mcp.aerostack.dev/s/aerostack/mcp-firecrawl

Sub-50ms globally · Zero cold start

Publisher

@aerostack verified

Pre-built functions for the most common MCP tool patterns. Clone, extend, and deploy.

Frequently asked questions

What is the Firecrawl MCP server and what can it do? +

The Firecrawl MCP server is hosted on Aerostack and exposes these tools to your AI agent: `_ping`, `scrape`, `crawl`, `crawl_status`, `map`. You get one hosted URL — no self-hosting — that works from Claude, Cursor, ChatGPT, Gemini, VS Code, or any MCP-compatible client, and you can share it with your team or combine it with other MCP servers in a workspace.

Is the Firecrawl MCP server hosted, or do I have to run it myself? +

It's hosted on Aerostack's edge infrastructure — you don't deploy or maintain anything. Add it to a workspace and you get one authenticated URL, with secrets encrypted, that any AI agent or editor can connect to. Use it solo or share the same URL across your whole team.

Which AI agents and editors can use the Firecrawl MCP server? +

Any MCP client: Claude and Claude Code, Cursor, ChatGPT, Gemini, Windsurf, Cline, VS Code, and custom agents. Because it's one hosted URL, the same Firecrawl MCP server works everywhere — and you can compose it with other MCP servers, skills, and functions behind a single workspace URL.

How do I install the Firecrawl MCP server in Claude Desktop? +

Add the following to your Claude Desktop config (`claude_desktop_config.json`): ```json { "mcpServers": { "@aerostack/mcp-firecrawl": { "command": "npx", "args": ["-y", "@aerostack/@aerostack/mcp-firecrawl"] } } } ``` Then restart Claude Desktop and the tools will appear automatically.

How do I use the Firecrawl MCP server in Cursor? +

In Cursor, open **Settings → MCP** and add: ```json { "name": "@aerostack/mcp-firecrawl", "command": "npx", "args": ["-y", "@aerostack/@aerostack/mcp-firecrawl"] } ``` Save and reload Cursor. The MCP tools will be available in Agent mode.

Does Firecrawl MCP require authentication? +

Yes. Firecrawl requires authentication. Check the MCP's documentation for the required credentials.

Firecrawl MCP Server — Hosted Web Search Integration

description Overview

mcp-firecrawl — Firecrawl Web Scraping MCP Server

What You Can Do

Available Tools

Configuration

Quick Start

Add to Aerostack Workspace

Example Prompts

Direct API Call

Security Notes

License

terminal Tools (7)

Details

Publisher

Tags

More in Web Search

Elasticsearch

Google Ads

Google Sheets

Webflow

Google Docs

Google Meet

Frequently asked questions