firecrawl-mcp-server and apify-mcp-server

These are competitors offering overlapping web scraping capabilities for LLM agents, with Apify providing access to pre-built task-specific scrapers while Firecrawl offers a more general-purpose web extraction API.

firecrawl-mcp-server
64
Established
apify-mcp-server
64
Established
Maintenance 17/25
Adoption 10/25
Maturity 16/25
Community 21/25
Maintenance 25/25
Adoption 10/25
Maturity 9/25
Community 20/25
Stars: 5,738
Forks: 641
Downloads:
Commits (30d): 9
Language: JavaScript
License: MIT
Stars: 888
Forks: 115
Downloads:
Commits (30d): 66
Language: TypeScript
License: MIT
No Package No Dependents
No Package No Dependents

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 apify-mcp-server

apify/apify-mcp-server

The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.

Implements both hosted HTTPS (with OAuth support and output schema inference) and local stdio transports compatible with Claude Desktop, VS Code, and Cursor, allowing AI agents to dynamically discover and invoke Apify Actors as MCP tools. Includes Skyfire agentic payment integration, enabling models to execute paid scraping tasks autonomously without requiring API tokens, and supports real-time tool discovery with capability detection across heterogeneous MCP clients.

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