Web Search API Eval

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

• 连接方式: 电脑或云端
• 传输方式: stdio, Streamable HTTP
• 分类: 搜索与 AI 记忆
• 你需要填写：YDC_API_KEY, TAVILY_API_KEY, EXA_API_KEY, PARALLEL_API_KEY

安装

选择你使用的 AI 应用，然后复制设置。

你需要

• 在云端运行无需安装任何东西，通过互联网连接
• npm已安装 Node.js（用于 npx 命令）

你用的是哪个应用？

https://websearch-api-eval.psberkeleymba.workers.dev/mcp

{
  "mcpServers": {
    "websearch-api-eval": {
      "command": "npx",
      "args": [
        "-y",
        "websearch-api-eval-mcp"
      ],
      "env": {
        "YDC_API_KEY": "your-value",
        "TAVILY_API_KEY": "your-value",
        "EXA_API_KEY": "your-value",
        "PARALLEL_API_KEY": "your-value"
      }
    }
  }
}

claude mcp add --transport http websearch-api-eval https://websearch-api-eval.psberkeleymba.workers.dev/mcp

claude mcp add websearch-api-eval --env YDC_API_KEY=your-value --env TAVILY_API_KEY=your-value --env EXA_API_KEY=your-value --env PARALLEL_API_KEY=your-value -- npx -y websearch-api-eval-mcp

{
  "mcpServers": {
    "websearch-api-eval": {
      "url": "https://websearch-api-eval.psberkeleymba.workers.dev/mcp"
    }
  }
}

{
  "mcpServers": {
    "websearch-api-eval": {
      "command": "npx",
      "args": [
        "-y",
        "websearch-api-eval-mcp"
      ],
      "env": {
        "YDC_API_KEY": "your-value",
        "TAVILY_API_KEY": "your-value",
        "EXA_API_KEY": "your-value",
        "PARALLEL_API_KEY": "your-value"
      }
    }
  }
}

{
  "servers": {
    "websearch-api-eval": {
      "type": "http",
      "url": "https://websearch-api-eval.psberkeleymba.workers.dev/mcp"
    }
  }
}

{
  "servers": {
    "websearch-api-eval": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "websearch-api-eval-mcp"
      ],
      "env": {
        "YDC_API_KEY": "your-value",
        "TAVILY_API_KEY": "your-value",
        "EXA_API_KEY": "your-value",
        "PARALLEL_API_KEY": "your-value"
      }
    }
  }
}

https://websearch-api-eval.psberkeleymba.workers.dev/mcp

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

• YDC_API_KEY 机密 env
  Optional. You.com API key, used only by run_live_search
• TAVILY_API_KEY 机密 env
  Optional. Tavily API key, used only by run_live_search
• EXA_API_KEY 机密 env
  Optional. Exa API key, used only by run_live_search
• PARALLEL_API_KEY 机密 env
  Optional. Parallel API key, used only by run_live_search

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

工具名称和描述与服务器在 2026年11月7日 报告的完全一致。这些内容由作者撰写，不是我们写的；我们以纯文本形式显示。

• get_overall_results

  Headline findings and the overall scorecard across all 30 queries (90 calls per API): accuracy, fully correct, precision@5, freshness, empty responses, failed calls, latency p50/p95, cost per correct answer. Also the per-use-case summary, which API fits which agent, and developer

• get_scorecard

  Full metric scorecard for one use case (gtm, insurance, finance) or 'overall'. Metrics: search-only latency p50/p95 (server and client), calls under 1 s, accuracy, freshness (% in window, newest relevant result age), content in one call, tokens, search cost.

• compare_providers

  Compare two or more of You.com, Tavily, Exa and Parallel side by side, overall or within one use case, optionally filtered to metrics whose name contains a keyword (e.g. 'latency', 'accuracy', 'fresh', 'cost', 'empty').

• recommend_provider

  Which web search API fits an agent, based on this benchmark: live voice/chat turns, deep research, semantic or long-tail queries, docs lookups, or a specific use case (GTM, insurance, finance). Returns the guidance with the supporting numbers.

• list_questions

  The 30 benchmark questions (G1-G10 GTM, I1-I10 insurance, F1-F10 finance): ID, what the agent is asked, the search call and freshness.

• get_question

  One benchmark question by ID (e.g. G3, I4, F5): the task, search call, parameters, answer key with sources, and what each API returned with its accuracy score (0-2, mean of 3 runs).

• get_charts

  The published graphs: overall scorecard, key metrics and per-query grids for GTM, insurance and finance, and developer activation. Without chart_id, lists them with titles and image links; with chart_id, also returns the image.

• get_methodology

  How the benchmark was run and graded: query design, identical request parameters, 3 runs per query, latency timing, SimpleQA and FreshQA grading, the 10 metrics and the standards they follow, and limits.

• how_to_run_locally

  How to rerun this benchmark on your own machine with your own API keys, including on your own queries. Nothing runs on this server.

• search

  Search the Web Search API Eval benchmark (results, questions, methodology, charts, how to run). Returns matching document IDs, titles and URLs.

• fetch

  Full text of one benchmark document by its ID (for example question-F5, scorecard-finance, overall, methodology).

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日

• ✓ 通过

  作者与仓库一致

  注册名称已通过 GitHub 账户 psinglap 验证，该账户拥有此仓库

• … 尚未检查

  仍在维护

  我们还没有从 GitHub 读取这个仓库

• … 尚未检查

  有许可证

  我们还没有从 GitHub 读取这个仓库

• ✓ 通过

  端点有响应

  在 204 毫秒内响应（HTTP 200）

• – 不适用

  使用 OAuth 登录

  无需登录

• ✓ 通过

  工具描述中没有隐藏指令

  已读取 11 个工具描述，未发现针对 AI 的隐藏指令

与“搜索与 AI 记忆”中的其他服务器比较i

• 星标数多于此分类中其他 5668 个服务器的 0%
• 发布到注册中心的时间比此分类中其他 5668 个服务器的 77% 更新
• 基础检查结果等于或优于此分类中其他 5668 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

作者的 README

claude mcp add websearch-api-eval -- npx -y websearch-api-eval-mcp

{

cd mcp