ENFRESDE
List your agent

Web Search API Eval

MCP server · hosted · v1.0.0 · io.github.psinglap/websearch-api-eval
Online · tested 1h agoNEW · 2h agoSeen in the registry 1h ago

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

Website ↗Source code ↗How to connect ↓

What it does

Web Search API Eval is an MCP server, a connector that lets an AI assistant use it as a tool. It is hosted: an assistant connects to it over the internet, nothing to install.

From the publisher's description, Electra Index matched it to one capability: web research. That makes it a candidate for tasks such as fact-check a document or find influencers.

Facts come from the Official MCP Registry, as declared by the publisher. Capabilities are matched automatically (low confidence). None of this is a test of the tool.

At a glance

Hosted (remote)YES
Local installNO
Version1.0.0
PriceNot in the registry
First seen27 Oct 2026
Last checked1h ago

How to connect

As declared in the Official MCP Registry · hosted endpoint tested by Electra Index 1h ago (live check)

Hosted endpoint

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

In Claude Code: claude mcp add --transport http web-search-api-eval https://websearch-api-eval.psberkeleymba.workers.dev/mcp

MCP settings (Claude Desktop, Cursor and other MCP clients)

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

Live check

Electra Index connected to the hosted endpoint 1h ago

ONLINE Web Search API Eval answered an MCP connection on 27 Oct 2026 and introduced itself as websearch-api-eval 1.1.0 (MCP protocol 2025-06-18).

11 tools offered to AI assistants

  • 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, w
  • 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, to
  • 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 numbe
  • 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).

What "online" means: the server answered an MCP connection at the time of the check. It is not a guarantee of security, quality or continuous uptime. How we test: we open an MCP session and ask for the tool list, as an AI assistant would. We never run a tool and never send a key. Checked every few days. Method

Is this your server? Monitoring Pro: a check every 30 minutes and an email within the hour when it stops answering. Launch offer: $39.99 once, for life.

Tasks it helps with

Share of each task's required capabilities it covers
Fact-check a document
Web Research
50%
Find influencers
Web Research
50%
Find leads
Web Research
50%
Monitor news on a topic
Web Research
50%
Optimize for AI search (GEO)
Web Research
33%
Analyze real estate
Web Research
33%
Build a literature review
Web Research
33%
Compare products online
Web Research
33%

Similar tools

Listed for the same task: fact-check a document
  • BrowsingBeeREMOTELOCAL
    Hosted browser for agents: open pages, search the web, extract data, read PDFs and take screenshots
  • VeilQuotaREMOTELOCAL
    Private OCR, web search, and attested AI chat, paid with anonymous credits bought with shielded ZEC
  • SyftlyREMOTELOCAL
    Ranks the best AI tool or API per task: transcription, TTS, web search, scraping and OCR
  • MCP Search ServerREMOTELOCAL
    Web search, content extraction, PDF parsing, plus datetime and geolocation tools. No API keys
  • Quant Agent ShopREMOTELOCAL
    Search, filings, sanctions, company, domain, email, SEO and weather tools, paid per call over x402
  • MarginaliaREMOTELOCAL
    Marginalia MCP — independent web search over a non-commercial, non-SEO index

Ready-made AI agents

An MCP server is a connector you add to your own assistant. These are finished products that do the same job for you:

Facts & evidence

Each fact shows where it was seen and when.
FactValueEvidenceSourceLast confirmed
Hosted endpointhttps://websearch-api-eval.psberkeleymba.workers.dev/mcpDECLAREDSRC-001 Official MCP Registry1h ago
Local install (package)noDECLAREDSRC-001 Official MCP Registry1h ago
Remote access (hosted)yesDECLAREDSRC-001 Official MCP Registry1h ago
Websitehttps://psinglap.github.io/websearch-api-eval/DECLAREDSRC-001 Official MCP Registry1h ago
Repositoryhttps://github.com/psinglap/websearch-api-evalDECLAREDSRC-001 Official MCP Registry1h ago
Registry statusactiveDECLAREDSRC-001 Official MCP Registry1h ago
Version1.0.0DECLAREDSRC-001 Official MCP Registry1h ago
MCP serveryesDECLAREDSRC-001 Official MCP Registry1h ago

Change history

  • NEW27 Oct 2026
    first seen in the index

Is this page accurate?

Flag it and our robot re-checks the official source. Reports never change a score.

Are you the publisher of Web Search API Eval?

Free · show your listing

An independent listing builds trust with your buyers. Announce it, and add the badge to your website or README.

Announce it on LinkedInListed on Electra Index
<a href="https://electraindex.com/mcp/web-search-api-eval?utm_source=badge&utm_medium=share&utm_campaign=listing"><img src="https://electraindex.com/api/badge/web-search-api-eval" alt="Listed on Electra Index"></a>

Questions about Web Search API Eval

How do I connect Web Search API Eval?

Use the hosted endpoint https://websearch-api-eval.psberkeleymba.workers.dev/mcp in your assistant's MCP settings. The exact settings are in "How to connect" above, as declared in the Official MCP Registry.

What tools does Web Search API Eval offer?

When Electra Index connected on 27 Oct 2026, it listed 11 tools: get_overall_results, get_scorecard, compare_providers, recommend_provider, list_questions, get_question, get_charts, get_methodology and more. The full list is in "Live check" above.

Is Web Search API Eval online?

Yes. Its hosted endpoint answered an MCP connection from Electra Index 1h ago.

What can I use Web Search API Eval for?

Based on its description, it is most relevant to: fact-check a document, find influencers, find leads, monitor news on a topic.