ZapFetch MCP Server
An APAC-native web scraping API for AI agents that provides tools for scraping, crawling, searching, and extracting structured data from websites, directly usable from MCP-compatible clients like Claude Desktop, Cursor, and Windsurf.
README
@zapfetch/mcp-server
MCP (Model Context Protocol) server for ZapFetch — APAC-native web scraping API for AI agents.
Use ZapFetch directly from Claude Desktop, Cursor, Windsurf, and any other MCP-compatible client.
Tools
zapfetch_scrape— scrape a single URLzapfetch_search— web search with optional content extractionzapfetch_crawl— crawl a website (async, returns job_id)zapfetch_crawl_status— poll crawl job progresszapfetch_map— discover URLs on a site (fast, no content)zapfetch_extract— extract structured data with a prompt + schemazapfetch_extract_status— poll extract job progress
Docs: https://docs.zapfetch.com
For docs lookups, Claude/Cursor/Windsurf can also use the auto-generated Mintlify MCP at https://docs.zapfetch.com/mcp.
Prerequisites
- Node.js 20+
- A ZapFetch API key (get one here)
Install
npm install -g @zapfetch/mcp-server
Configure
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"zapfetch": {
"command": "npx",
"args": ["-y", "@zapfetch/mcp-server"],
"env": {
"ZAPFETCH_API_KEY": "zf-your-api-key"
}
}
}
}
Cursor
Edit ~/.cursor/mcp.json:
{
"mcpServers": {
"zapfetch": {
"command": "npx",
"args": ["-y", "@zapfetch/mcp-server"],
"env": { "ZAPFETCH_API_KEY": "zf-your-api-key" }
}
}
}
Windsurf
Edit ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"zapfetch": {
"command": "npx",
"args": ["-y", "@zapfetch/mcp-server"],
"env": { "ZAPFETCH_API_KEY": "zf-your-api-key" }
}
}
}
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
ZAPFETCH_API_KEY |
yes | — | Your ZapFetch API key |
ZAPFETCH_API_URL |
no | https://api.zapfetch.com |
Override for self-host / dev |
Usage Examples
After configuration, just ask your AI assistant:
- "Scrape the top 3 posts from news.ycombinator.com/newest"
- "Find me the latest TypeScript release notes on github.com"
- "Crawl docs.example.com and summarize the authentication section"
- "Extract product name, price, and stock from these 5 rakuten.co.jp URLs as JSON"
Migrating from Firecrawl MCP
ZapFetch is Firecrawl-compatible at the API level, but this MCP uses zapfetch_* tool names (not firecrawl_*) to avoid conflicts if you run both. Capabilities are 1:1 — just update prompts referring to tool names.
Development
pnpm install # or npm install
npm run typecheck
npm run build # -> dist/
Local test with Claude Desktop pointed at your build:
{
"mcpServers": {
"zapfetch-dev": {
"command": "node",
"args": ["/absolute/path/to/zapfetch-mcp/dist/index.js"],
"env": { "ZAPFETCH_API_KEY": "zf-..." }
}
}
}
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。