Explore
Evidence for your next connection.
Independent measurements of remote MCP servers. Every observation has a timestamp.
Read-only probesMCP server · Data access / search
Web search API benchmark for AI agents: You.com, Tavily, Exa, Parallel. Results and charts.
0 failed · 7 not measured
Median of successful probes over 7 days
Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.
Tool definitions returned by this server
Independent monitoring
Responded
The server completed its last measured handshake. This is an observation, not a guarantee.
Last checked| Test area | Passed | Failed | Unmeasured |
|---|---|---|---|
ConnectionCan a client connect and discover tools? | 5 | 0 | 0 |
Reliability & speedDoes it respond consistently and quickly? | 1 | 0 | 3 |
Access & authenticationWhat is required to use this server? | 1 | 0 | 2 |
Tool qualityAre the tool definitions usable by an agent? | 4 | 0 | 0 |
Publisher identityCan the publisher be traced to its source? | 4 | 0 | 2 |
Unmeasured means there is not enough evidence to decide. How these checks work
Start using Web Search API Eval
Choose your client, copy the configuration, then enable the server in your client’s MCP settings.
Run this command in your terminal, then restart Claude Code.
Claude Code
claude mcp add --transport http web-search-api-eval https://websearch-api-eval.psberkeleymba.workers.dev/mcpCapabilities
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').
DiscoveredFull text of one benchmark document by its ID (for example question-F5, scorecard-finance, overall, methodology).
DiscoveredThe 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.
DiscoveredHow 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.
DiscoveredHeadline 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.
DiscoveredOne 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).
DiscoveredFull 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.
DiscoveredHow to rerun this benchmark on your own machine with your own API keys, including on your own queries. Nothing runs on this server.
DiscoveredThe 30 benchmark questions (G1-G10 GTM, I1-I10 insurance, F1-F10 finance): ID, what the agent is asked, the search call and freshness.
DiscoveredWhich 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.
DiscoveredSearch the Web Search API Eval benchmark (results, questions, methodology, charts, how to run). Returns matching document IDs, titles and URLs.
DiscoveredRecent measurements
| Checked | Result | Response | Tools |
|---|---|---|---|
| Connected | 80 ms | 11 | |
| Connected | 79 ms | 11 |