MCP Server Firecrawl

@modelcontextprotocol/mcp-server-firecrawl

A Model Context Protocol (MCP) server that provides web scraping and intelligent content searching capabilities using the Firecrawl API. This server enables AI agents to extract structured data from websites and perform content searches.

Features

  • Web Scraping: Extract content from any URL with customizable options
  • Content Search: Perform intelligent searches across web content
  • Markdown Output: Get results in clean, formatted markdown
  • Ad Blocking: Optional ad blocking during scraping
  • Custom Actions: Support for custom scraping actions

Installation

npm install -g @modelcontextprotocol/mcp-server-firecrawl

Configuration

  1. Get your Firecrawl API key from api.firecrawl.dev
  2. Set your API key as an environment variable:
export FIRECRAWL_API_KEY=your-api-key
  1. Start the server:
mcp-server-firecrawl

Tools

scrape_url

Scrape content from a URL with customizable options.

interface ScrapeUrlArgs { url: string; // URL to scrape jsonOptions?: { prompt: string; // Prompt for extracting specific information }; formats?: string[]; // Output formats (e.g. ["markdown"]) actions?: string[]; // Custom scraping actions blockAds?: boolean; // Whether to block ads during scraping }

Example:

const result = await client.callTool({ name: "scrape_url", arguments: { url: "https://example.com", jsonOptions: { prompt: "Extract the main article content", }, formats: ["markdown"], blockAds: true } });

search_content

Search content using Firecrawl's intelligent search capabilities.

interface SearchContentArgs { query: string; // Search query scrapeOptions?: { formats?: string[]; // Output formats (e.g. ["markdown"]) }; limit?: number; // Maximum number of results (1-100) }

Example:

const result = await client.callTool({ name: "search_content", arguments: { query: "latest developments in AI", scrapeOptions: { formats: ["markdown"] }, limit: 5 } });

Development

  1. Clone the repository:
git clone https://github.com/yourusername/mcp-server-firecrawl.git cd mcp-server-firecrawl
  1. Install dependencies:
npm install
  1. Build the project:
npm run build
  1. Run tests:
npm test

Contributing

Contributions are welcome! Please read our Contributing Guidelines for details on how to submit pull requests, report issues, and contribute to the project.

Documentation

License

This project is licensed under the MIT License - see the LICENSE file for details.

You must be authenticated.

A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

A server that provides web scraping and intelligent content searching capabilities using the Firecrawl API, enabling AI agents to extract structured data from websites and perform content searches.

  1. Features
    1. Installation
      1. Configuration
        1. Tools
          1. scrape_url
            1. search_content
            2. Development
              1. Contributing
                1. Documentation
                  1. License