# Web Search API Eval

- Registry name: `io.github.psinglap/websearch-api-eval` · version 1.1.0
- Categories (automatic, keyword rules): Web search, Search & data, Monitoring & logs, Infrastructure & security
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.psinglap%2Fwebsearch-api-eval
- Server page: https://mcpstation.net/s/io.github.psinglap--websearch-api-eval.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

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

## Tools (as reported by the server, not verified)

- `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\_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 \(for example question-F5, scorecard-finance, overall, methodology\).

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html