# Web Search API Eval

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

- name: io.github.psinglap/websearch-api-eval
- version: 1.1.0
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 91/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.psinglap%2Fwebsearch-api-eval
- tools: https://api.protogrid.dev/v1/servers/io.github.psinglap%2Fwebsearch-api-eval/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "websearch-api-eval": {
      "type": "http",
      "url": "https://websearch-api-eval.psberkeleymba.workers.dev/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-11d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 91/100 (strong)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 11 of 11 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,427 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: deps.dev does not know websearch-api-eval-mcp@1.1.0

- tools: 11, about 1,427 tokens to load them all
- tool set hash: 8aaf5d90328cfec4a2d995258305b698
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.psinglap/websearch-api-eval.svg)](https://protogrid.dev/servers/io.github.psinglap/websearch-api-eval)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Dependencies

- npm websearch-api-eval-mcp@1.1.0: unknown

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://websearch-api-eval.psberkeleymba.workers.dev/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

- npm websearch-api-eval-mcp@1.1.0 secrets: YDC_API_KEY, TAVILY_API_KEY, EXA_API_KEY, PARALLEL_API_KEY

## Tools (11)

- `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.