Token导航 LogoToken导航TokenDH.com
SC
AI代理HTTP官方级别未说明来源级核验

scrapegraphai

MCP Server

The ScrapeGraphAI MCP Server is a production-ready Model Context Protocol (MCP) server that connects Large Language Models (LLMs) to the ScrapeGraph AI API. It enables AI assistants like Claude and C…

工具数

公开资料未说明
JavaScriptAPI密钥HTTPAI代理

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

最后核验

2026/5/17 23:41

运行时

Node.js

快速接入

先看主来源和安装命令,再打开仓库或文档;下面只保留这个条目的关键接入事实。

命令预览

npx -y smithery mcp add scrapegraphai-inc/sgai

详细介绍

scrapegraphai

The ScrapeGraphAI MCP Server is a production-ready Model Context Protocol (MCP) server that connects Large Language Models (LLMs) to the ScrapeGraph AI API. It enables AI assistants like Claude and C…

Quick Start

# Connect this server (installs CLI if needed)
npx -y smithery mcp add scrapegraphai-inc/sgai

# Browse available tools
npx -y smithery tool list scrapegraphai-inc/sgai

# Get full schema for a tool
npx -y smithery tool get scrapegraphai-inc/sgai extract

# Call a tool
npx -y smithery tool call scrapegraphai-inc/sgai extract '{}'

Direct MCP Connection

Endpoint: https://sgai--scrapegraphai-inc.run.tools

Required config:

  • X-API-Key (header) — Your ScrapeGraph API Key get it from https://scrapegraphai.com/dashboard/api-keys

Tools (17)

  • extract — Extract structured data from a webpage using AI (API v2 POST /extract).
  • search — AI-powered web search with structured data extraction (API v2 POST /search).
  • crawl_start — Start an asynchronous multi-page crawl (API v2 POST /crawl).
  • crawl_get_status — Retrieve the results of an asynchronous SmartCrawler operation.
  • crawl_stop — Stop a running crawl job (API v2 POST /crawl/:id/stop).
  • crawl_resume — Resume a stopped crawl job (API v2 POST /crawl/:id/resume).
  • credits — Return remaining API credits (API v2 GET /credits).
  • history — List recent API requests (API v2 GET /history).
  • monitor_create — Create a scheduled monitor job (API v2 POST /monitor).
  • schema — Generate or augment a JSON Schema from a natural-language prompt
  • monitor_list — List monitors (API v2 GET /monitor).
  • monitor_get — Get one monitor by id (API v2 GET /monitor/:id).
  • monitor_pause — Pause a monitor (API v2 POST /monitor/:id/pause).
  • monitor_resume — Resume a paused monitor (API v2 POST /monitor/:id/resume).
  • monitor_delete — Delete a monitor (API v2 DELETE /monitor/:id).
  • monitor_activity — Poll per-run tick history for a monitor (API v2 GET /monitor/:id/activity).
  • scrape — Fetch page content (API v2 POST /scrape).
# Get full input/output schema for a tool
npx -y smithery tool get scrapegraphai-inc/sgai 

Resources

  • scrapegraph://api/status — Current status and capabilities of the ScapeGraph API server.
  • scrapegraph://examples/use-cases — Common use cases and example implementations for ScapeGraph tools.
  • scrapegraph://parameters/reference — Comprehensive parameter reference guide for all ScapeGraph MCP tools.
  • scrapegraph://tools/comparison — Detailed comparison of ScapeGraph tools to help choose the right tool for each task.

Prompts (2)

  • web_scraping_guide — A comprehensive guide to using ScapeGraph's web scraping tools effectively.
  • quick_start_examples — Quick start examples for common ScapeGraph use cases.

目录标签

目录标签

JavaScriptAPI密钥HTTPAI代理

接入字段

传输方式(transport,传输协议)

HTTP

鉴权方式(authType,认证方式)

api-key

运行时(runtime,运行环境)

Node.js

权限和风险

HTTPapi-key部署方式未说明

接入前请确认传输方式、认证方式和部署位置,并根据实际工具能力限制访问范围。

安装前确认

不要直接授予不必要的文件、网络或账号权限;先核对安装命令和配置内容。

仍需确认:category

来源信息

继续浏览同类 MCP