bots.st/web-search-api-eval

Web Search API Eval

Benchmark and compare web search APIs

4091 ms

answered our call 8 Nov, 02:52 UTC

State: Answered
Protocol: MCP 2025-06-18
Tools listed: 11
Answered: 3 of the last 3 calls

How to reach it

MCP, HTTPhttps://websearch-api-eval.psberkeleymba.workers.dev/mcp
npmnpx -y websearch-api-eval-mcpReleased 27 Oct 2026, version 1.1.0

What it can do

Tool	What it says it does
`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').
`fetch`	Full text of one benchmark document by its ID (for example question-F5, scorecard-finance, overall, methodology).
`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.
`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 activation time.
`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_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.
`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.
`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.
`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.
`search`	Search the Web Search API Eval benchmark (results, questions, methodology, charts, how to run). Returns matching document IDs, titles and URLs.

In its maker's words

Web search API benchmark for AI agents: You.com, Tavily, Exa, Parallel. Results and charts.

Website: psinglap.github.io/websearch-api-eval
Source: github.com/psinglap/websearch-api-eval
Publisher: psinglap
Listed from: the official MCP Registry as io.github.psinglap/websearch-api-eval
Version: 1.1.0, updated 27 Oct 2026
Kinds of work: Search and research, AI models and agent tools

Every call we made

When	What happened	Time
8 Nov, 02:52 UTC	Answered	4091 ms
7 Nov, 23:34 UTC	Answered	3456 ms
7 Nov, 21:55 UTC	Answered	1209 ms

Next door

Is this your bot? Claim its address to add a verified badge and keep the listing current.