What does Scrapi do that alternatives don’t?
Scrapi provides clean, LLM-ready Markdown/Text output with JavaScript rendering, metadata, and built-in billing – no need for separate proxies or parsing libraries.
Scrapi MCP Server
@bamchi
Scrapi MCP Server について
🔗 MCP server that converts URLs to clean Markdown/Text for LLM agents
Scrapi MCP Server の設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"scrapi": {
"command": "npx",
"args": [
"-y",
"@scrapi.ai/mcp-server"
],
"env": {
"SCRAPI_API_KEY": "your-api-key"
}
}
}
}Scrapi MCP Server のツール
5Scrapes a webpage and returns the content in AI-readable Markdown format. Can access blocked sites through browser rendering.
Scrapes multiple webpages in parallel and returns the content in AI-readable Markdown format. Can access blocked sites through browser rendering.
Check API usage and remaining credits. Returns current plan, subscription credits, purchased credits, and total remaining credits.
Check the status of all ScraperServer instances. Shows server health, circuit breaker state, failure counts, and last success/failure times.
Retrieve MCP billing information: subscription details, available plans, daily usage history, or spending limits.
概要
What is Scrapi?
Scrapi is an MCP server that converts URLs into clean Markdown or plain text for LLM agents, enabling AI tools to fetch and read web pages directly. It is built on 8+ years of web scraping expertise and provides fast, reliable content extraction.
How to use Scrapi?
Install via npx or from source, then configure your MCP client (Claude Desktop, Cline, Cursor, Claude Code) with the provided JSON configuration. Obtain an API key from scrapi.ai/dashboard (free plan available) and set SCRAPI_API_KEY or pass --api-key. Use tools like scrape_url or scrape_urls to fetch content.
Key features of Scrapi
- URL to Markdown with preserved headings, lists, links
- URL to plain text extraction
- Metadata extraction (title, author, date, images)
- Clean output – no ads, navigation, or scripts
- JavaScript rendering for single-page applications
- Built-in billing with credit tracking and subscription management
- Auto-retry on 429 rate limit responses
- Dual transport: Stdio and Streamable HTTP
Use cases of Scrapi
- AI agents summarizing online articles for research
- Chatbots retrieving and citing live web content
- Automated content monitoring and data gathering
- Extracting structured information from documentation pages
よくある質問
What are the runtime requirements?
A Node.js 20+ environment is needed for Stdio mode; Streamable HTTP transport works without Node.js on the client side.
Where is my data processed and stored?
The README does not specify data storage location; API calls are handled by scrapi.ai servers. Self-hosting the HTTP server is also possible (advanced).
Are there rate limits or usage caps?
Yes. The free plan includes 500 credits per month. Rate limit responses (429) are automatically retried using Retry-After headers.
What authentication does Scrapi use?
Authentication is via an API key (`hsmcp_` prefix) set as environment variable `SCRAPI_API_KEY` or passed as `--api-key` CLI argument, or via Bearer token header for Streamable HTTP.
「その他」の他のコンテンツ
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
26.0K
MCP Toolbox for Databases
googleapisMCP Toolbox for Databases is an open source MCP server for databases.
15.9K
Glasswarp
GlasswarpSee and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
Yuppsy
Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Hindsight
vectorize-ioHindsight: Agent Memory That Learns
50.4K
コメント