Novada MCP

io.github.NovadaLabs由 GitHub 账号 NovadaLabs 发布v0.9.46更新于 Nov 7, 2026

One MCP server for all web data. Scrape, search, crawl, and AI research in one install.

已验证Streamable HTTP可网页运行网页搜索与抓取云端与基础设施数据与分析

概览

AI 生成的概览

Novada MCP 让助手通过 Novada 代理网络进行网页搜索、页面提取、爬取和 14 个平台的结构化抓取，并支持带引用的研究。

可以做什么
  • 按查询搜索网页，支持引擎、时间、域名和地区筛选
  • 从单个或最多 10 个已知网址提取内容，可自动升级绕过反爬
  • 执行多来源研究，返回带编号的来源段落
  • 通过各平台专用工具抓取 14 个平台的结构化记录
  • 爬取同一站点内有限数量的相关页面并发现站点网址
  • 将自有 HTTP 客户端经由指定 IP 类型、国家或会话路由
适用场景
当助手需要实时网页数据时适用：价格或商品对比、招聘与线索调研、多来源带引用的回答，或无需自行解析 HTML 即可获取特定平台记录。页面拦截普通抓取、需要代理路由控制时也适合。
运行要求
需要 Novada 账号和 API 密钥，通过 Authorization Bearer 请求头或 OAuth 提供；托管端点为 mcp.novada.com，也可用 npx novada-mcp 本地运行。用量计入 Novada 账户，提供起步免费额度。基础提取无需密钥，但不含渲染升级。
安装前请注意
用量计入 Novada 账户且无每月调用上限，费用可能累积。API 密钥为机密，经 Authorization 请求头传递，不应放入网址。代理子账户、IP 白名单、静态 IP 和密钥捕获等写操作需两步审批令牌。抓取数据经 Novada 代理网络取自第三方网站。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Novada MCP，将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 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。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.NovadaLabs%2Fnovada-mcp/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "novada": {
      "type": "http",
      "url": "https://mcp.novada.com/mcp"
    }
  }
}

README

Novada MCP

Web search, page extraction and structured platform data for AI agents, backed by Novada's own proxy network.

[npm version] [npm downloads] [CI] [License: MIT]

[Free to start — $10 in free credits, usage billed to your Novada account, no credit card needed]

Free to start: $10 in free credits, no credit card. There is no monthly call cap — usage is billed to your Novada account.

What it is good at

  • Structured data from 14 sources, no HTML parsing. One typed tool per platform (Amazon, Google, LinkedIn, TikTok, YouTube, Instagram, Facebook, X, Walmart, GitHub and more). The operation is a closed list, so a wrong value is rejected before any call and the error lists the valid ones.
  • Pages that block bots. novada_extract escalates from a plain fetch to JS render to a real browser on its own, takes up to 10 URLs per call, and names the blocker when it cannot get through (for example anti_bot:kasada).
  • Cited research in one call. novada_research runs several searches, de-duplicates, and returns numbered source passages for your agent to write the answer from. It returns source material, not a generated summary.

Try these prompts

Use caseAsk your agent
Price research"Compare the top 5 Amazon results for 'standing desk' by price and rating, then check the cheapest one on Walmart."
Lead research"List open Data Analyst jobs on LinkedIn in Germany posted this week, with company and link."
Cited answer"What changed in the EU battery regulation this year? Give me sources I can quote."

Quickstart

Hosted, nothing to install. Sign up at novada.com for a key; check your balance any time with novada_setup.

claude.ai: Settings → Connectors → Add custom connector, paste https://mcp.novada.com/mcp, sign in with your Novada account (OAuth).

Claude Code:

bash
claude mcp add --transport http novada https://mcp.novada.com/mcp --header "Authorization: Bearer YOUR_KEY"

Cursor, Windsurf, VS Code and self-host (npx -y novada-mcp): see the install guide. The hosted endpoint accepts the key only in an Authorization: Bearer header or via OAuth, never in a URL.

How to choose a tool

[How to choose a Novada MCP tool — decision guide]

ToolUse it when
novada_searchFind pages by query (google / duckduckgo / yandex; time, domain, geo filters).
novada_extractRead one known URL, or up to 10 in parallel, through anti-bot pages.
novada_researchAnswer a complex question with passages from several sources in one call.
novada_scrapeStructured records from 14 platforms, plus 14 typed per-platform tools such as novada_scrape_amazon and novada_scrape_linkedin.
novada_crawlPull content from a bounded set of related pages (up to 20) on one site.
novada_mapDiscover what URLs exist on a site before fetching.
novada_proxyRoute your own HTTP client through a specific IP type, country or session.

Not sure? Call novada_discover. 37 tools self-hosted; the hosted endpoint exposes 29 of them (self-host adds browser automation, site copy, and the write-gated open/renew static-IP actions). Full list and per-surface availability: docs/TOOLS.md.

How it compares

Typed platform scrapersSearch / extract / crawl / mapOwn proxy networkNotes
NovadaYes (14)Yes, plus researchYesProxy config from Novada's own network via novada_proxy
TavilyNoYesNoSearch, extract, map, crawl
FirecrawlNoYesNoScrape, crawl, search, extract and an agent tool
Bright DataYesYesYesClosest in scope

Pick Tavily or Firecrawl if you only need search and page-to-markdown. Pick Novada or Bright Data if you also need records from specific platforms or control over proxy routing. Comparison reflects each project's public MCP README as of 2026-10-26; check theirs for current details.

Built for agents: write operations (proxy sub-accounts, IP whitelist, static IPs, key capture) use a two-step approval token, and novada_discover and novada_setup let an agent find the right tool or check its key without reading this page. Basic novada_extract also works without a key (no render escalation).

Repository layout

npm-package/ is the novada-mcp package and holds all tool logic. hosted-server/ is the HTTP wrapper behind mcp.novada.com. distribution/ holds plugin and registry packaging plus the release consistency check, monitoring/ the smoke, stress and report tooling, config/ the surface definitions, scripts/ repo-level checks, and docs/ the tool reference and assets. See ARCHITECTURE.md and CONTRIBUTING.

Links

novada.com · npm · GitHub · Issues

License

MIT, see LICENSE.

来源：README.md，提交 5d9f8ab

工具

0
该服务器需要登录，因此 SourceWeft 无法在没有账号的情况下读取其工具，也未收录。已连接账号所能看到的内容可能因账号及其权限而异。

版本历史

7
  1. v0.9.46最新Nov 7, 2026
  2. v0.9.45Nov 1, 2026
  3. v0.9.44Oct 26, 2026
  4. v0.9.43Oct 26, 2026
  5. v0.9.42Oct 22, 2026
  6. v0.9.41Oct 18, 2026
  7. v0.9.39Sep 16, 2026

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分