firecrawl-mcp-server and scrapegraph-mcp

These are competitors—both provide MCP servers for web scraping, but Firecrawl offers more comprehensive features (LLM-optimized markdown conversion, search capabilities) and broader client integration, while ScrapeGraphAI focuses specifically on AI-powered graph-based scraping.

firecrawl-mcp-server
64
Established
scrapegraph-mcp
61
Established
Maintenance 17/25
Adoption 10/25
Maturity 16/25
Community 21/25
Maintenance 10/25
Adoption 14/25
Maturity 18/25
Community 19/25
Stars: 5,738
Forks: 641
Downloads:
Commits (30d): 9
Language: JavaScript
License: MIT
Stars: 58
Forks: 20
Downloads: 394
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No risk flags

About firecrawl-mcp-server

firecrawl/firecrawl-mcp-server

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

Implements MCP (Model Context Protocol) server using stdio transport with optional HTTP Streamable mode, exposing Firecrawl's scraping, crawling, search, and agent-browser automation capabilities as callable tools. Supports both cloud and self-hosted Firecrawl instances with configurable retry logic, exponential backoff, and credit usage monitoring. Integrates directly with Cursor, Claude Desktop, VS Code, and Windsurf through standardized MCP server configuration.

About scrapegraph-mcp

ScrapeGraphAI/scrapegraph-mcp

ScapeGraph MCP Server

Implements an MCP server exposing 8 web scraping tools—from basic markdown conversion to agentic multi-step workflows—that integrate with the ScrapeGraph AI API for structured data extraction, infinite scroll handling, and JavaScript rendering. Deploys via Smithery for seamless Claude Desktop and Cursor integration, with both local and remote hosting options. Supports asynchronous multi-page crawling, custom output schemas, and persistent sessions for complex extraction workflows.

Scores updated daily from GitHub, PyPI, and npm data. How scores work