Firecrawl

🚀 MCP Firecrawl Server

This is a simple MCP server that provides tools for website scraping and structured data extraction using the Firecrawl API.

🚀 Quick Start

📦 Installation

1. Install dependencies:

npm install

2. Create a .env file in the root directory and add the following variables:

FIRECRAWL_API_TOKEN=your_token_here
SENTRY_DSN=your_sentry_dsn_here

• FIRECRAWL_API_TOKEN (Required): Your Firecrawl API token.
• SENTRY_DSN (Optional): Sentry DSN for error tracking and performance monitoring.

3. Start the server:

npm start

Or start the server by setting environment variables directly through the command line:

FIRECRAWL_API_TOKEN=your_token_here npm start

✨ Features

• Website Scraping: Extract content from websites, supporting multiple formats.
• Structured Data Extraction: Extract specific data points based on custom schemas.
• Error Tracking: Integrate Sentry for error tracking and performance monitoring.

💻 Usage Examples

Basic Usage

The server provides two tools:

1. scrape-website: Basic website scraping, supporting multiple output formats.
2. extract-data: Structured data extraction based on prompts and schemas.

Tool: scrape-website

This tool scrapes a website and returns the content in the desired format.

Parameters:

• url (string, required): The URL of the website to scrape.
• formats (array of strings, optional): An array of desired output formats. Supported formats include:
  • "markdown" (default)
  • "html"
  • "text"

Example using MCP Inspector:

# Basic usage (default is Markdown)
mcp-inspector --tool scrape-website --args '{
  "url": "https://example.com"
}'

# Multiple formats
mcp-inspector --tool scrape-website --args '{
  "url": "https://example.com",
  "formats": ["markdown", "html", "text"]
}'

Tool: extract-data

This tool extracts structured data from websites based on the provided prompts and schemas.

Parameters:

• urls (array of strings, required): A list of URLs to extract data from.
• prompt (string, required): A prompt describing the data to extract.
• schema (object, required): A schema defining the data to extract.

The schema definition is an object where the keys are field names and the values are types. Supported types include:

• "string": Text fields.
• "boolean": Boolean values (true/false).
• "number": Numbers.
• Arrays: Specified as ["type"], where type is any of the above types.
• Objects: Nested objects with their own type definitions.

Example using MCP Inspector:

# Basic example to extract company information
mcp-inspector --tool extract-data --args '{
  "urls": ["https://example.com"],
  "prompt": "Extract the company mission, whether it supports SSO, and whether it is open source.",
  "schema": {
    "company_mission": "string",
    "supports_sso": "boolean",
    "is_open_source": "boolean"
  }
}'

# Complex example to extract nested data
mcp-inspector --tool extract-data --args '{
  "urls": ["https://example.com"],
  "prompt": "Extract detailed user information including name, age, and address.",
  "schema": {
    "user": {
      "name": "string",
      "age": "number",
      "address": {
        "street": "string",
        "city": "string",
        "country": "string"
      }
    }
  }
}'

📚 Documentation

Troubleshooting

1. Ensure that the API token and Sentry DSN (if used) are set correctly.
2. Check your network connection to ensure that you can access the target website.
3. Check the console output or log files for more error information.