Web Search API Eval
概览
作者提供的说明(英文原文)
Web search API benchmark for AI agents: You.com, Tavily, Exa, Parallel. Results and charts.
PopNx MCP 的三大支柱
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i4 项中通过 4 项依据公开信息检查;尚未扫描代码
- 使用情况i起步阶段↓ 69/周 · ★ 3
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。
安装之前
- 基础检查:4 项中通过 4 项
- 在作者的服务器上运行:你向它提出的内容会经过他们的服务器。
- 可以做 11 件事(工具) get_overall_results, get_scorecard, compare_providers, recommend_provider …
- 需要你自己填写:
YDC_API_KEY,TAVILY_API_KEY,EXA_API_KEY,PARALLEL_API_KEY
标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
- 打开 Settings → Connectors
- 点击 Add custom connector
- 粘贴下面的地址,然后点击 Add
- 如果要求登录,请登录作者的服务
https://websearch-api-eval.psberkeleymba.workers.dev/mcp或者在你的电脑上运行
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"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"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http websearch-api-eval https://websearch-api-eval.psberkeleymba.workers.dev/mcp或者在你的电脑上运行
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运行前请先填写空着的值。
或者自己复制设置
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"websearch-api-eval": {
"url": "https://websearch-api-eval.psberkeleymba.workers.dev/mcp"
}
}
}或者在你的电脑上运行
或者自己复制设置
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"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"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"websearch-api-eval": {
"type": "http",
"url": "https://websearch-api-eval.psberkeleymba.workers.dev/mcp"
}
}
}或者在你的电脑上运行
或者自己复制设置
粘贴到项目中的 .vscode/mcp.json
{
"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"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
- 打开网页版 ChatGPT → Settings → Connectors (Apps)
- 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
- 粘贴下面的地址,起个名字,然后保存
- 如果要求登录,请登录作者的服务
https://websearch-api-eval.psberkeleymba.workers.dev/mcp菜单名称可能因套餐和版本不同而略有差异。
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
- Optional. You.com API key, used only by run_live_search
- Optional. Tavily API key, used only by run_live_search
- Optional. Exa API key, used only by run_live_search
- 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。
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
通过互联网连接,适用于
ClaudeChatGPTGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatOpen WebUIRaycast
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它能做什么
工具名称和描述与服务器在 2026年11月10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_resultsHeadline 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_scorecardFull 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_providersCompare 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_providerWhich 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_questionsThe 30 benchmark questions (G1-G10 GTM, I1-I10 insurance, F1-F10 finance): ID, what the agent is asked, the search call and freshness.
get_questionOne 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_chartsThe 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_methodologyHow 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_locallyHow to rerun this benchmark on your own machine with your own API keys, including on your own queries. Nothing runs on this server.
searchSearch the Web Search API Eval benchmark (results, questions, methodology, charts, how to run). Returns matching document IDs, titles and URLs.
fetchFull 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11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
- ✓ 通过
仍在维护
代码最后更新于14天前
- … 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 141 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 5868 个服务器的 84%
- 发布到注册中心的时间比此分类中其他 5868 个服务器的 72% 更新
- 基础检查结果等于或优于此分类中其他 5868 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。
常见问题
Web Search API Eval 安全吗?
它在 4 项适用的基础检查中通过了 4 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
它需要哪些密钥或代码?
你需要填写:YDC_API_KEY, TAVILY_API_KEY, EXA_API_KEY, PARALLEL_API_KEY
它在我的电脑上运行还是在云端?
两种方式都可以:安装在你的电脑上,或者连接云端版本。
它还在维护吗?
GitHub 仓库最后更新于14天前,最新版本(1.1.0)于15天前进入注册中心。
哪些应用可以使用它?
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
有什么可以替代它?
同一分类中有:Ruflo, Context7, Metabase
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:↓ 每周下载量i★ 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
打开 README
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Web Search API Eval: MCP server
An MCP server that lets Claude, ChatGPT, Cursor and other AI assistants answer questions about the Web Search API Eval benchmark (You.com, Tavily, Exa and Parallel on 30 agent queries), and run your own live search spot checks.
Use it two ways:
| Hosted (no install) | Local (npm) | |
|---|---|---|
| Connect | https://websearch-api-eval.psberkeleymba.workers.dev/mcp | npx -y websearch-api-eval-mcp |
| Works in | Claude, ChatGPT, any remote MCP client | Claude Desktop, Claude Code, Cursor, VS Code, any stdio MCP client |
| Benchmark tools | ✅ | ✅ |
run_live_search with your own keys | — | ✅ |
Install
Claude Code
claude mcp add websearch-api-eval -- npx -y websearch-api-eval-mcp
Claude Desktop, Cursor, VS Code (add to the client's MCP config):
{
"mcpServers": { "websearch-api-eval": { "command": "npx", "args": ["-y", "websearch-api-eval-mcp"], "env": { "YDC_API_KEY": "optional", "TAVILY_API_KEY": "optional", "EXA_API_KEY": "optional", "PARALLEL_API_KEY": "optional" } } } }
The keys are optional and only used by run_live_search. Leave out any provider you don't have a key for. Requires Node.js 18 or later.
Hosted, no install: in Claude, Settings → Connectors → Add custom connector → paste the hosted URL. In ChatGPT, create an app in Developer mode with the same URL and no authentication.
Tools
| Tool | Returns |
|---|---|
get_overall_results | Headline, overall scorecard, per-use-case summary, which API fits which agent, developer activation |
get_scorecard | Full scorecard for overall, gtm, insurance or finance |
compare_providers | Two or more providers side by side, optionally filtered by metric keyword |
recommend_provider | Which API fits an agent's need, with supporting numbers |
list_questions | The 30 questions, filterable by use case |
get_question | One question: task, search call, answer key, sources, what each API returned and its score |
get_charts | The published graphs; with chart_id, also the image |
get_methodology | How tests ran and were graded, the 10 metrics and their standards, limits |
how_to_run_locally | Steps and keys to rerun the full benchmark on your own machine |
search, fetch | Generic search and document fetch (used by ChatGPT research features) |
run_live_search (local only) | Sends one query to each provider using your own API keys and returns latency, result count and top results |
The benchmark tools are read-only and read the published results (run Oct 8, 2026). run_live_search calls the providers directly from your machine with your keys and uses your own credits; a single call is a spot check, not a graded benchmark. For the full graded run, use the harness.
Example questions
- "Which web search API is fastest for a voice agent?"
- "Compare Exa and Parallel on finance."
- "What was question F5 and who got it right?"
- "Show me the overall scorecard chart."
- "Run a live search for 'FOMC minutes' and compare the providers."
Data and updates
Results come from data/*.json on the published site, built from the Evaluation page by data/build_data.py. After a new benchmark run, rebuild the data and push; both the hosted and npm servers pick it up with no redeploy or new release.
Develop
cd mcp
npm install npx wrangler dev # hosted server locally at http://localhost:8787/mcp npm run build # npm package entry at dist/cli.js npx @modelcontextprotocol/inspector@0.17.2 node dist/cli.js # call tools by hand npx wrangler deploy # deploy the hosted server npm publish # publish the npm package
Built with the official MCP TypeScript SDK. Registry entry: io.github.psinglap/websearch-api-eval (server.json).
Privacy and support
No sign-in, no cookies, no storage, no request logging. Privacy Policy · Terms · Support · MIT License