Web Search API Eval 远程 MCP 服务器是什么?
Web Search API Eval 的远程 MCP 服务器是一个托管的 Model Context Protocol 端点,地址是 https://websearch-api-eval.psberkeleymba.workers.dev/mcp,AI 助手无需在本地安装或运行任何东西即可连接。
@Web Search API Eval
基本信息
A read-only MCP server for a live benchmark of four web search APIs for AI agents (You.com, Tavily, Exa and Parallel) on 30 agent-style queries across GTM, insurance and finance. Engineers choosing a search API for an agent can ask for scorecards, side-by-side comparisons, per-query answer keys, charts and methodology, then rerun the benchmark themselves. Free, no sign-in. Nothing calls a search API or stores data; results are the published snapshot from the Oct 8, 2026 run.
https://websearch-api-eval.psberkeleymba.workers.dev/mcpclaude mcp add web-search-api-eval --transport http https://websearch-api-eval.psberkeleymba.workers.dev/mcpHeadline 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 activation time.
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 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').
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.
The 30 benchmark questions (G1-G10 GTM, I1-I10 insurance, F1-F10 finance): ID, what the agent is asked, the search call and freshness.
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).
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.
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 rerun this benchmark on your own machine with your own API keys, including on your own queries. Nothing runs on this server.
Search the Web Search API Eval benchmark (results, questions, methodology, charts, how to run). Returns matching document IDs, titles and URLs.
Full text of one benchmark document by its ID (for example question-F5, scorecard-finance, overall, methodology).
A read-only MCP server for a live benchmark of four web search APIs for AI agents (You.com, Tavily, Exa and Parallel) on 30 agent-style queries across GTM, insurance and finance. Engineers choosing a search API for an agent can ask for scorecards, side-by-side comparisons, per-query answer keys, charts and methodology, then rerun the benchmark themselves. Free, no sign-in. Nothing calls a search API or stores data; results are the published snapshot from the Oct 8, 2026 run.
From the publisher's website: You.com, Tavily, Exa and Parallel compared live on 30 agent-style queries across GTM, insurance and finance: accuracy, freshness, latency and setup friction.
https://websearch-api-eval.psberkeleymba.workers.dev/mcp (Streamable HTTP)Claude Code:
claude mcp add web-search-api-eval --transport http https://websearch-api-eval.psberkeleymba.workers.dev/mcp
Other clients (mcpServers config):
{ "mcpServers": { "web-search-api-eval": { "type": "http", "url": "https://websearch-api-eval.psberkeleymba.workers.dev/mcp" } } }
Read from the server's tools/list on 2026-11-13:
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 answerget_scorecard — Full metric scorecard for one use case (gtm, insurance, finance) or 'overall'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.grecommend_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)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 freshnessget_question — One benchmark question by ID (e.gget_charts — The published graphs: overall scorecard, key metrics and per-query grids for GTM, insurance and finance, and developer activationget_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 limitshow_to_run_locally — How to rerun this benchmark on your own machine with your own API keys, including on your own queriessearch — Search the Web Search API Eval benchmark (results, questions, methodology, charts, how to run)fetch — Full text of one benchmark document by its ID (for example question-F5, scorecard-finance, overall, methodology)initialize request when checked on 2026-11-13.Sources: Website, Submission.
Web Search API Eval 的远程 MCP 服务器是一个托管的 Model Context Protocol 端点,地址是 https://websearch-api-eval.psberkeleymba.workers.dev/mcp,AI 助手无需在本地安装或运行任何东西即可连接。
把端点 https://websearch-api-eval.psberkeleymba.workers.dev/mcp 添加到任意支持 MCP 的客户端,比如 Claude Code、Cursor 或 VS Code。本页的接入代码块可以一步配置好每个客户端。
不需要。Web Search API Eval 的 MCP 服务器不需要认证——直接用端点地址连接即可。
Web Search API Eval 暴露的是 streamable-http 端点,这是远程 MCP 服务器普遍使用、主流客户端都支持的传输方式。
Read-only, source-backed AI model pricing, history, comparisons and cost calculations.
Official 42min MCP server: let Claude, ChatGPT, Cursor or any MCP client manage your meeting scheduling. Check availability, find free slots, book, cancel and reschedule meetings, manage recurring series, secret booking
Production remote MCP server with 35 safe web-intelligence tools: 32 paid x402 URL operations plus 3 free discovery/demo tools. Base Mainnet USDC, no account or API key; SSRF protection, strict schemas and idempotent set
AI Video MCP by AITuber is a hosted MCP server that lets AI agents create and publish video. You connect it once, then ask your agent for a video in plain language. It writes the script, picks a voice, generates the visu
Find venues and submit booking inquiries through MCP.
评论