Firecrawl Simple MCP Server

by Sacode

386 downloads Not rated yet MIT license
GitHub

About

MCP server for Firecrawl Simple — a web scraping and site mapping tool enabling LLMs to access and process web content

Details

License
MIT license

Explore

- Web Scraping: Scrape content from any URL with JavaScript rendering support.
- Website Mapping: Generate a sitemap of a given site.
- Simplified Architecture: Optimized codebase with consistent patterns and improved error handling.
- Type Safety: Strong typing throughout the codebase with Zod schema validation.
- Configurable: Customize behavior through environment variables.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Firecrawl Simple MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Before installing and using Firecrawl Simple MCP Server, ensure you have:

- Node.js 16.x or higher installed
- Access to a running Firecrawl Simple API instance
- Sufficient permissions to install global npm packages (if installing globally)

npm install -g firecrawl-simple-mcp

FIRECRAWL_API_URL=http://localhost:3002/v1 firecrawl-simple-mcp


FIRECRAWL_API_URL=http://localhost:3002/v1 firecrawl-simple-mcp

FIRECRAWL_API_URL=http://localhost:3002/v1 \
FIRECRAWL_LOG_LEVEL=DEBUG \
firecrawl-simple-mcp

Error: Authentication failed: Invalid API key

Solution:

- Verify that the FIRECRAWL_API_KEY is correct
- Check if the API requires authentication
- Contact the API administrator for valid credentials

- Robust environment variable handling with validation.
- Fallback to sensible defaults when configuration is invalid.
- Clear error messages for configuration issues.
- Centralized configuration module.

npm install

url

(required): The URL to scrape.

formats

Array of output formats to return. Options include "markdown", "html", and "rawHtml".

waitFor

Time to wait for JavaScript execution in milliseconds.

timeout

Request timeout in milliseconds.

includeTags

HTML tags to include in the result.

excludeTags

HTML tags to exclude from the result.

headers

Custom HTTP headers to send with the request.

mobile

Whether to use a mobile viewport.

search

Search term to filter URLs.

ignoreSitemap

Whether to ignore sitemap.xml.

includeSubdomains

Include subdomains in mapping.

limit

Maximum number of URLs to map.

Scrape content from a single URL with JavaScript rendering support.

{
  "name": "firecrawl_scrape",
  "arguments": {
    "url": "https://example.com",
    "formats": ["markdown", "html", "rawHtml"],
    "waitFor": 1000,
    "timeout": 30000,
    "includeTags": ["article", "main"],
    "excludeTags": ["nav", "footer"],
    "headers": {
      "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
      "Accept-Language": "en-US,en;q=0.9"
    },
    "mobile": false
  }
}

Parameters:

- url (required): The URL to scrape.
- formats: Array of output formats to return. Options include "markdown", "html", and "rawHtml".
- waitFor: Time to wait for JavaScript execution in milliseconds.
- timeout: Request timeout in milliseconds.
- includeTags: HTML tags to include in the result.
- excludeTags: HTML tags to exclude from the result.
- headers: Custom HTTP headers to send with the request.
- mobile: Whether to use a mobile viewport.

Generate a sitemap of a given site.

{
  "name": "firecrawl_map",
  "arguments": {
    "url": "https://example.com",
    "search": "optional search term",
    "ignoreSitemap": true,
    "includeSubdomains": false,
    "limit": 5000
  }
}

Parameters:

- url (required): The URL to map.
- search: Search term to filter URLs.
- ignoreSitemap: Whether to ignore sitemap.xml.
- includeSubdomains: Include subdomains in mapping.
- limit: Maximum number of URLs to map.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "firecrawl simple mcp server": {
            "firecrawl-simple-mcp": {
                "command": "npx",
                "args": [
                    "-y",
                    "firecrawl-simple-mcp"
                ],
                "env": {
                    "FIRECRAWL_API_URL": "http://localhost:3002/v1"
                }
            }
        }
    }
}

McpServers

{
    "firecrawl-simple-mcp": {
        "command": "npx",
        "args": [
            "-y",
            "firecrawl-simple-mcp"
        ],
        "env": {
            "FIRECRAWL_API_URL": "http://localhost:3002/v1"
        }
    }
}

A Model Context Protocol (MCP) server for Firecrawl Simple, a powerful web scraping and site mapping tool that enables Large Language Models (LLMs) to access and process web content.

Project Links

- GitHub Repository
- npm Package

Table of Contents

- Prerequisites
- Quick Start
- Features
- Installation
- Usage
- Configuration
- Available Tools
- Troubleshooting
- Note on Crawl Functionality
- Architecture Improvements
- Development
- Testing
- Contributing
- License

Prerequisites

Before installing and using Firecrawl Simple MCP Server, ensure you have:

- Node.js 16.x or higher installed
- Access to a running Firecrawl Simple API instance
- Sufficient permissions to install global npm packages (if installing globally)

Quick Start

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.