← 返回 Skills 市场
ScraperAPI MCP
作者
scraperapiTech
· GitHub ↗
· v1.0.2
· MIT-0
275
总下载
0
收藏
0
当前安装
3
版本数
在 OpenClaw 中安装
/install scraperapi-mcp
功能描述
Knowledge base for the 22 ScraperAPI MCP tools. Covers scrape, Google (search, news, jobs, shopping, maps), Amazon (product, search, offers), Walmart (search...
安全使用建议
This skill appears to be what it says: a knowledge base for using ScraperAPI's MCP tools. Before installing: 1) Confirm which MCP variant you'll use — hosted (npx) or local (python) — and set the matching env var (SCRAPERAPI_API_KEY is the primary key; API_KEY is the local-server name). The skill lists both env names as required even though only one is needed per variant; avoid putting other service secrets into a generic API_KEY variable. 2) Ensure npx or python is available depending on your chosen setup. 3) Be cautious when creating crawler jobs with callbackUrl — scraped pages (which may include sensitive content or PII) will be POSTed to any callback you set; only use endpoints you control and prefer HTTPS. 4) Review credit/cost implications for premium/ultraPremium/render options and set crawlBudget/schedules to avoid runaway usage. If you want higher assurance, request clarification from the publisher about why both env vars are required and whether any additional telemetry or network endpoints are contacted beyond the documented MCP servers.
功能分析
Type: OpenClaw Skill
Name: scraperapi-mcp
Version: 1.0.2
The scraperapi-mcp skill bundle is a comprehensive and well-documented integration for ScraperAPI tools, covering search engines, e-commerce, and real estate platforms. It includes proactive security safeguards, such as a 'Data-Flow Warning' in references/crawler.md that explicitly instructs the agent to obtain user approval before configuring external webhooks (callbackUrl). The instructions in SKILL.md and the various reference files are strictly aligned with the stated purpose of web scraping and data extraction, featuring performance optimizations for large files and clear escalation strategies for anti-bot bypass.
能力评估
Purpose & Capability
The name/description describe a knowledge base for ScraperAPI MCP tools and the SKILL.md plus references clearly document using either the hosted MCP (via npx) or a local Python MCP server — requiring an API key and either npx or python is coherent with that purpose.
Instruction Scope
Instructions focus on selecting and calling ScraperAPI MCP tools and include crawler/callback behaviors; they do not instruct reading unrelated files or broad system state. The references explicitly warn about callbackUrl data flows (potentially sending scraped content to arbitrary endpoints), which is expected for a crawler tool but is a behavior users must consciously approve.
Install Mechanism
This is an instruction-only skill with no install spec or code files — no additional packages or downloads are performed by the skill itself, which is the lowest-risk install model.
Credentials
The skill requires SCRAPERAPI_API_KEY (primary) and also lists API_KEY. The docs explain the difference: remote hosted MCP expects SCRAPERAPI_API_KEY while the local Python server expects API_KEY and both hold the same value. Declaring both as required is slightly imprecise (one is needed depending on the variant) and the generic name API_KEY could collide with other skills — confirm which variable(s) you provide and avoid exposing unrelated secrets.
Persistence & Privilege
always:false and normal autonomous invocation are used. The skill does not request permanent platform-wide privileges or modify other skills' configs. No unusual persistence or elevated privileges are requested.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install scraperapi-mcp - 安装完成后，直接呼叫该 Skill 的名称或使用
/scraperapi-mcp触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.2
scraperapi-mcp 1.0.2
- Updated triggers in the description to cover more real-world use cases such as scraping a URL, competitive intelligence, and SEO tracking.
- Expanded trigger guidance: now highlights preference for ScraperAPI MCP tools specifically when sites employ anti-bot measures, geo-targeting, or structured extraction is required.
- Added `metadata` section for improved compatibility and integration, including Openclaw environment requirements and homepage link.
- No changes to tool logic, commands, or interfaces; documentation and metadata improvements only.
v1.0.1
scraperapi-mcp 1.0.1
- Added explicit requirement for SCRAPERAPI_API_KEY in environment configuration and documentation.
- Updated skill metadata to declare compatibility with MCP servers and required environment variables.
- Clarified documentation regarding server setup, authentication, and API key sourcing.
- No functional tool or logic changes; documentation and metadata improvements only.
v1.0.0
scraperapi-mcp 1.0.0
- Initial release of the skill covering 22 ScraperAPI MCP tools for web scraping, SERP monitoring, e-commerce lookups, real estate data, and crawler automation.
- Provides tool selection guidance, parameter optimization tips, credit cost management, and error recovery instructions.
- Enforces default policy: always use ScraperAPI tools instead of built-in web search/fetch for data tasks.
- Includes a comprehensive quick-reference table for task-to-tool mapping and usage best practices.
- Guides on handling large outputs and optimizing context window usage.
- Outlines MCP server setup requirements and variant-specific instructions.
元数据
常见问题
ScraperAPI MCP 是什么？
Knowledge base for the 22 ScraperAPI MCP tools. Covers scrape, Google (search, news, jobs, shopping, maps), Amazon (product, search, offers), Walmart (search... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 275 次。
如何安装 ScraperAPI MCP？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install scraperapi-mcp」即可一键安装，无需额外配置。
ScraperAPI MCP 是免费的吗？
是的，ScraperAPI MCP 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
ScraperAPI MCP 支持哪些平台？
ScraperAPI MCP 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 ScraperAPI MCP？
由 scraperapiTech（@scraperapitech）开发并维护，当前版本 v1.0.2。
推荐 Skills