Scrapewise

ai.scrapewisev0.1.1更新于 Oct 6, 2026

Scrape, clean and match product and price data from any website

已验证Streamable HTTP可网页运行Web Search & ScrapingBusiness & CommerceData & Analytics

概览

AI 生成的概览

让助手构建、运行并读取托管网页抓取器,从任意网站采集并清洗商品与价格数据。

功能
Scrapewise 是一个用于抓取商品与价格数据的托管 MCP 服务器。助手可以通过它预览页面,并根据 URL 或 cURL 命令创建抓取器、定义要提取的列,把抓取器按项目分组并维护链接列表,运行单个抓取器、整个分组或临时 URL 列表,并读取样本行、完整结果集、运行历史和每次运行的列。它还涵盖货币换算、单位价格归一化等后处理规则、以锚定竞品为参照的价格监控、计划任务、数据保留、SEO 字段以及 API 密钥管理。
适用场景
当助手需要从网站获取结构化的商品或价格数据、又不想自行编写和托管抓取代码时适用,例如创建并重复运行抓取器、监控竞品价格,或导出清洗后的结果集用于分析。
运行要求
需要可访问网络的远程 Streamable HTTP 端点 Scrapewise 账号,并在 Settings > API Keys 中创建 API 密钥,以 Authorization 头按 Bearer <密钥> 形式发送。无需本地运行时或安装软件包。
安装前请注意
Authorization 头携带 Scrapewise API 密钥,应视为机密,不要外泄。计费为按量付费,运行和导出可能产生费用。许多工具会写入或删除数据,包括创建和删除抓取器、分组、站点、结果数据、分类、模式、增强数据和 API 密钥,以及启动或停止运行;部分删除操作提供预览版本。抓取的页面内容和 URL 会发送到 Scrapewise 服务。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Scrapewise,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "scrapewise": {
      "type": "http",
      "url": "https://mcp.scrapewise.ai/mcp"
    }
  }
}

README

ScrapeWise MCP Server

Scrape, clean and match product and price data from any website — from inside your AI agent.

ScrapeWise runs a hosted Model Context Protocol server. You point your MCP client at one URL, add your API key, and your agent can build scrapers, run them, and read the results back as structured data.

  • Endpoint: https://mcp.scrapewise.ai/mcp
  • Transport: Streamable HTTP
  • Registry name: ai.scrapewise/scrapewise (official MCP registry)
  • Auth: Authorization: Bearer <your API key>
  • Docs: scrapewise.ai/mcp

This repository holds the connection manifest and the per-client config for that server. The server itself is hosted — there is nothing here to install or run.

Get an API key

Sign up at scrapewise.ai, then go to Settings → API Keys and create one. Pricing is pay-as-you-go.

Connect

Replace YOUR_SCRAPEWISE_API_KEY in every snippet below.

Claude Code

bash
claude mcp add scrapewise --transport http https://mcp.scrapewise.ai/mcp \  --header 'Authorization: Bearer YOUR_SCRAPEWISE_API_KEY'

Claude Desktop

claude_desktop_config.json:

json
{  "mcpServers": {    "scrapewise": {      "url": "https://mcp.scrapewise.ai/mcp",      "headers": {        "Authorization": "Bearer YOUR_SCRAPEWISE_API_KEY"      }    }  }}

Cursor

Same shape, in ~/.cursor/mcp.json:

json
{  "mcpServers": {    "scrapewise": {      "url": "https://mcp.scrapewise.ai/mcp",      "headers": {        "Authorization": "Bearer YOUR_SCRAPEWISE_API_KEY"      }    }  }}

VS Code

VS Code is the odd one out: the map is servers, not mcpServers, and a remote server has to name its transport with "type": "http". Get either wrong and VS Code skips the entry without telling you.

Open the Command Palette → MCP: Open User Configuration, then:

json
{  "servers": {    "scrapewise": {      "type": "http",      "url": "https://mcp.scrapewise.ai/mcp",      "headers": {        "Authorization": "Bearer YOUR_SCRAPEWISE_API_KEY"      }    }  }}

Anything else

Any client that speaks Streamable HTTP works. Give it the endpoint, the Authorization header, and the name scrapewise.

What your agent can do

AreaWhat it covers
BuildPreview a page, create a scraper from a URL or a cURL command, define the columns to extract
OrganiseGroup scrapers by project, add product URLs to a scraper's link list, share groups
RunRun one scraper, a whole group, or an ad-hoc list of URLs; stop a run; read run errors
ReadPull sample rows, full result sets, run history and per-run columns; export a group
TransformGroup-level post-process rules — currency conversion, quantity normalisation, price per unit
MonitorSchedules, price monitoring with anchor competitors, data-quality and retention settings

Tools

The server advertises its own tool list once connected, so this is a reference rather than the source of truth. What a given API key sees can differ. Full documentation at docs.scrapewise.ai.

Build a scraper

scrapewise_preview_scraper_from_url · scrapewise_preview_scraper_from_curl · scrapewise_preview_scraper_preview_rule · scrapewise_create_scraper · scrapewise_create_scraper_v2 · scrapewise_create_file_scraper · scrapewise_get_scraper · scrapewise_get_scraper_v2 · scrapewise_get_scraper_list · scrapewise_get_scraper_config_parameters · scrapewise_update_scraper_schema · scrapewise_update_scraper_fallback · scrapewise_update_file_scraper_file · scrapewise_delete_scraper · scrapewise_delete_scraper_preview

Organise scrapers and their URLs

scrapewise_create_scraper_group · scrapewise_get_scraper_group_list · scrapewise_delete_scraper_group · scrapewise_delete_scraper_group_preview · scrapewise_create_scraper_site · scrapewise_get_scraper_site · scrapewise_get_scraper_site_links · scrapewise_update_scraper_site_from_source · scrapewise_delete_scraper_site · scrapewise_get_scraper_sitemaps · scrapewise_get_scraper_shared_group_list · scrapewise_list_scraper_shared_group_list · scrapewise_update_scraper_shared_group

Run

scrapewise_run_scraper · scrapewise_run_scraper_group · scrapewise_run_scraper_url_list · scrapewise_run_scraper_data_group · scrapewise_run_scraper_sitemaps_harvest · scrapewise_stop_scraper · scrapewise_stop_scraper_group · scrapewise_stop_scraper_shared_group · scrapewise_get_scraper_load_history · scrapewise_get_scraper_job_errors · scrapewise_get_scraper_load_site · scrapewise_get_scraper_load_site_content

Read the data

scrapewise_get_scraper_sample_data · scrapewise_get_scraper_data_group · scrapewise_get_scraper_data_group_client · scrapewise_get_scraper_data_group_categories · scrapewise_update_scraper_data_group_category · scrapewise_delete_scraper_data_group_category · scrapewise_delete_scraper_data_group_category_preview · scrapewise_get_run_columns · scrapewise_get_run_columns_batch · scrapewise_export_scraper_data_group · scrapewise_delete_scraper_data · scrapewise_delete_scraper_data_preview

Clean and convert

scrapewise_get_scraper_group_post_process_rules · scrapewise_update_scraper_group_post_process_rules · scrapewise_update_scraper_group_currency · scrapewise_update_scraper_group_ai_control · scrapewise_update_scraper_group_data_quality · scrapewise_create_customer_schema · scrapewise_list_customer_schema · scrapewise_delete_customer_schema · scrapewise_delete_customer_schema_preview

Monitor prices

scrapewise_update_scraper_group_price_monitor · scrapewise_get_scraper_group_price_monitor_anchor_competitors · scrapewise_update_scraper_group_price_monitor_anchor_competitor · scrapewise_delete_scraper_group_price_monitor_anchor_competitor · scrapewise_list_scraper_group_price_monitor_picks · scrapewise_update_scraper_group_price_monitor_pick · scrapewise_delete_scraper_group_price_monitor_pick

Schedule and retain

scrapewise_update_scraper_group_schedule · scrapewise_update_scraper_group_start_type · scrapewise_update_scraper_group_retention · scrapewise_update_scraper_retention

Enrichment and SEO fields

scrapewise_get_enrichment · scrapewise_delete_enrichment · scrapewise_list_enrichable_scrapers · scrapewise_get_scraper_seo_fields · scrapewise_search_scraper_seo_fields

Account

scrapewise_create_api_key · scrapewise_list_api_keys · scrapewise_delete_api_key

Manifest

server.json is a mirror. The authority is https://scrapewise.ai/server.json, which is generated from the ScrapeWise site repo and checked by its test suite. If the two ever disagree, the hosted one is right.

Namespace ownership for ai.scrapewise/* is proved by the Ed25519 public key published at https://scrapewise.ai/.well-known/mcp-registry-auth.

Support

Licence

MIT — see LICENSE. Covers this repository's contents only, not the hosted service.

来源:README.md,提交 5c87d5c

工具

0
工具元数据尚未被收录。

版本历史

1
  1. v0.1.1最新Oct 6, 2026