Firecrawl

Provides web scraping, search, site crawling, mapping, and data extraction via the Firecrawl API.

typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-msparihar_mcp-server-firecrawl": {
      "command": "mcp-server-firecrawl",
      "args": [],
      "env": {
        "FIRECRAWL_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You can deploy and operate the Firecrawl MCP Server to perform web scraping, content search, site crawling, site mapping, and data extraction through the Firecrawl API. It enables automated data collection workflows, configurable outputs, and scalable integration with MCP clients you use.

How to use

Connect to the Firecrawl MCP Server from your MCP client and call the available actions to scrape pages, crawl sites, map site structures, or extract data. You can run the server locally and provide your API key to authorize requests. Use the standard MCP workflow to trigger tasks, pass parameters for URLs, depth, formats, and prompts, and receive structured results in your preferred formats.

How to install

Prerequisites: Node.js and npm must be installed on your system. You will install the MCP server package globally for easy access or install it in a local project.

# Global installation
npm install -g @modelcontextprotocol/mcp-server-firecrawl

# Local project installation
npm install @modelcontextprotocol/mcp-server-firecrawl

Configuration and usage notes

Set your Firecrawl API key in your environment so the server can authorize requests from clients.

# Unix/Linux/macOS
export FIRECRAWL_API_KEY=your-api-key

# Windows (Command Prompt)
set FIRECRAWL_API_KEY=your-api-key

# Windows (PowerShell)
$env:FIRECRAWL_API_KEY = "your-api-key"

Starting the server

Run the Firecrawl MCP Server from your shell after installation. The server exposes MCP endpoints you can connect to from your MCP clients.

mcp-server-firecrawl

Configuration examples

If you integrate with a client such as Claude Desktop App or Claude VSCode Extension, you can point to the Firecrawl MCP Server and supply your API key. The examples below show the required structure.

{
  "firecrawl": {
    "command": "mcp-server-firecrawl",
    "env": {
      "FIRECRAWL_API_KEY": "your-api-key"
    }
  }
}

Security and best practices

Protect your API key and validate requests. Implement domain allowlisting, enforce rate limiting, and use secure error handling to prevent leakage of sensitive data.

Usage examples

You can perform web scraping, site crawling, site mapping, and data extraction by triggering specific actions from your MCP client. Use the provided arguments to specify URLs, depth limits, output formats, and extraction prompts.

Troubleshooting tips

If you encounter authentication errors, verify that FIRECRAWL_API_KEY is correctly set in the environment of the running server. Check that your MCP client is configured to connect to the running server and that you are using a supported action name and proper argument structure.

Notes

The server supports multiple actions like scraping, crawling, mapping, and extracting data. Refer to your MCP client’s capabilities to discover exact action names and argument formats.

Available tools

web_scrape

Scrape content from web pages with options like mobile emulation, ad blocking, filtering, and structured extraction.

content_search

Perform multi-language searches with location-based results and structured outputs.

site_crawl

Crawl websites with depth control, path filters, rate limiting, and progress tracking.

site_map

Generate site maps with subdomain support, link analysis, and visual hierarchy.

data_extract

Extract structured data from multiple URLs with schema validation and prompts.