Extrapify MCP Server

@christ0pper

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

christ0pper

投稿者

Chris Cleatus

Extrapify MCP Server について

Structured web context infrastructure for AI agents. Extract schema-guided structured JSON from websites using Claude-powered parsing and MCP-native workflows.

#mcp #claude-desktop #cursor #ai-agents #structured-data #ai-infrastructure #web-extraction#browserless#developer-tools #automation

Extrapify 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": {
    "extrapify": {
      "command": "node",
      "args": [
        "/absolute/path/to/extrapify-mcp/mcp/server.mjs"
      ],
      "env": {
        "EXTRAPIFY_API_BASE_URL": "https://extrapify.com",
        "EXTRAPIFY_API_KEY": "sk_live_your_key_here"
      }
    }
  }
}

Extrapify MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Extrapify?

Extrapify is a stateless MCP server that bridges MCP-compatible clients (Claude Desktop, Cursor, etc.) to the hosted Extrapify API. It provides a single tool to extract validated, typed JSON from any public webpage by defining a schema and providing a URL.

How to use Extrapify?

Install via npm, copy .env.example to .env, and set EXTRAPIFY_API_KEY and EXTRAPIFY_API_BASE_URL. Start the server with npm run mcp:start. In Claude Desktop, add a configuration block pointing to node mcp/server.mjs with those environment variables. The tool extract_structured_data accepts url, mode, and schema parameters.

Key features of Extrapify

One tool: extract_structured_data
Supports schema types: string, number, integer, float, boolean, date, datetime, url, and arrays
Modes: auto, single, list
Handles Browserless rendering for JS-heavy pages automatically
Production-ready bridge with no extraction logic or state
Works with any MCP client over stdio transport

Use cases of Extrapify

Extract article metadata (title, author, date) from news pages
Scrape product details (name, price, availability) from e‑commerce sites
Collect job listings (title, company, location) from career pages
Capture company data (industry, size, contact) from a business directory

よくある質問

What runtime or dependencies does Extrapify require?

Node.js is required. The MCP server runs over stdio and requires an API key from extrapify.com.

Where does the extracted data go? Does data live on the server?

Extraction is performed by the Extrapify API; the MCP server only forwards requests. The API handles fetching, rendering, extraction, and returns the result. The server itself is stateless.

How do I authenticate with Extrapify?

Set the `EXTRAPIFY_API_KEY` environment variable to your API key from extrapify.com/dashboard.

What if I get a 401 or 403 error?

Verify your API key is correct and active at extrapify.com/dashboard.

Can Extrapify handle JavaScript‑heavy pages?

Yes. The Extrapify API automatically falls back to Browserless rendering when pages rely on JavaScript. No action is needed on your side.

「その他」の他のコンテンツ

Glasswarp

See 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.

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Lemon.io

lemon-io

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3