{"id":736786,"recorded_at":"2026-10-28T03:29:29.485084Z","observed_at":"2026-10-28T03:29:29.484872Z","subject_kind":"endpoint","subject":"02837a79-9872-477f-b9f2-11f49d640ec8","kind":"mcp.tools","method":"probe.mcp/1","body":{"count":11,"tools":[{"description":"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').","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"metric_filter":{"description":"Optional keyword to keep only matching metrics","type":"string"},"providers":{"description":"Two or more of: You.com, Tavily, Exa, Parallel","items":{"enum":["You.com","Tavily","Exa","Parallel"],"type":"string"},"minItems":2,"type":"array"},"use_case":{"default":"overall","description":"overall, gtm, insurance or finance","enum":["overall","gtm","insurance","finance"],"type":"string"}},"required":["providers"],"type":"object"},"name":"compare_providers"},{"description":"Full text of one benchmark document by its ID (for example question-F5, scorecard-finance, overall, methodology).","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"id":{"description":"Document ID from search","type":"string"}},"required":["id"],"type":"object"},"name":"fetch"},{"description":"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.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"chart_id":{"description":"e.g. overall_scorecard, finance_key_metrics, gtm_query_grid, time_steps_activation","type":"string"},"use_case":{"default":"all","description":"Filter the list","enum":["all","gtm","insurance","finance","setup"],"type":"string"}},"type":"object"},"name":"get_charts"},{"description":"How the benchmark was run and graded: query design, identical request parameters, 3 runs per query, latency timing, SimpleQA and FreshQA grading, the 10 metrics and the standards they follow, and limits.","inputSchema":{"properties":{},"type":"object"},"name":"get_methodology"},{"description":"Headline findings and the overall scorecard across all 30 queries (90 calls per API): accuracy, fully correct, precision@5, freshness, empty responses, failed calls, latency p50/p95, cost per correct answer. Also the per-use-case summary, which API fits which agent, and developer activation time.","inputSchema":{"properties":{},"type":"object"},"name":"get_overall_results"},{"description":"One benchmark question by ID (e.g. G3, I4, F5): the task, search call, parameters, answer key with sources, and what each API returned with its accuracy score (0-2, mean of 3 runs).","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"id":{"description":"Question ID, e.g. G3, I4 or F5","type":"string"}},"required":["id"],"type":"object"},"name":"get_question"},{"description":"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.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"use_case":{"description":"overall, gtm, insurance or finance","enum":["overall","gtm","insurance","finance"],"type":"string"}},"required":["use_case"],"type":"object"},"name":"get_scorecard"},{"description":"How to rerun this benchmark on your own machine with your own API keys, including on your own queries. Nothing runs on this server.","inputSchema":{"properties":{},"type":"object"},"name":"how_to_run_locally"},{"description":"The 30 benchmark questions (G1-G10 GTM, I1-I10 insurance, F1-F10 finance): ID, what the agent is asked, the search call and freshness.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"use_case":{"default":"all","description":"all, gtm, insurance or finance","enum":["all","gtm","insurance","finance"],"type":"string"}},"type":"object"},"name":"list_questions"},{"description":"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.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"agent_need":{"description":"What the agent does, e.g. 'voice agent answering in under a second' or 'finance research'","type":"string"}},"type":"object"},"name":"recommend_provider"},{"description":"Search the Web Search API Eval benchmark (results, questions, methodology, charts, how to run). Returns matching document IDs, titles and URLs.","inputSchema":{"$schema":"http://json-schema.org/draft-07/schema#","properties":{"query":{"description":"What to look for","type":"string"}},"required":["query"],"type":"object"},"name":"search"}]},"body_sha256":"b7d64ec3baf3b9b4191c523a56afa140d4b816b980fbcf3007b75f287e4c5523","prev_id":null,"leaf":"0x8cce93724b19c7cac89783fa1fdb918b705fe83adc6b0e720f7080175274c435","leaf_text":"{\"body\":\"b7d64ec3baf3b9b4191c523a56afa140d4b816b980fbcf3007b75f287e4c5523\",\"id\":736786,\"kind\":\"mcp.tools\",\"method\":\"probe.mcp/1\",\"observed_us\":1793158169484872,\"prev\":null,\"subject\":\"02837a79-9872-477f-b9f2-11f49d640ec8\",\"subject_kind\":\"endpoint\"}","day":{"day":"2026-10-28","leaves":231336,"root":"0x2c19037464cc4c493624565f01775d6446fc78eaa118fc6865bfe2bfca9ff78e","chained":"0xd1d7dee8322ceff8f4c8d83aa1fe4a4466825c2af1c97dbde3d35db61234f7be","anchor_chain":"eip155:5042002","anchor_tx":"0x8bae2b1d097834c8b458513862d70d29ee807e98dc2e863b27250131c15b35ae","anchor_block":69584042},"proof":["0x8cce84c84e76e409c521adb2e4ee37493ac9f19888c8e4cbc45ee8fce43077b4","0x01000cbc0fe71d059446fd5e7cff48eea3f4eeeacabd515ab1fb2cc4cb9ddc66","0x00db5138deb523045734c71a02b8b805ff4fb3040c1d875af09cfc417025917b","0x30309772d20941ec13157bf13d1048b975d961e604c38bec69ef7a93d88e34c2","0xc365158d5c586d37dc57c755381c832270c345e54bba138e42c088b3def67d2b","0xf9ad6dfed470d3ade44c56f891c8164ec30d682ab5e6108356107906aa536e1a","0xf0ae7cc07456d5caeff1c70f4ebfe2296104dd816015f3a70828280ebde1bc23","0x238a4febd48aca99c2571499355550ae648ee3e49bd245c5a3d085436b9bf656","0x42c1def2e8e02bf1dfd8860e1ee725dd7da4ad8d942449bd95b735cce4cd324a","0x60b0d7a178f72fc3e21dac1cee2b9657b756f3f53b846cf9666ffff27ad3c163","0x629019a302eb28956efe0ab26b14729dbeb5be95de1124d8372526c03892aeaf","0x9560e0a6c078eef64083ffc1591f9aab803bac81e1815abba76b7711510818cb","0xdbb215681a11fa9a73d4086f7e02f913b35a590ef20bcbcc46a343cbef08a9da","0x115e196b75a0422533397227b51b9c807591ec2574919c03800bb0d253f110e8","0xe2f9c120d14f36fdddf9b4e605c5d0b8a13b835e2380472255dc22e14b93e84e","0x74cf00e07b52415c2184cf20be69d195ed2725497a6892c2f3e449497c17d0ec","0x7a743a0a09057bae687051274e1d45bf973bd36a1a4ba16a191b5d29e3bdfa2a","0xe027395fafb7fc41921c42ca0542524ea22204cbd5908b70b27f3d5fb26f5d0f"]}