{"data":{"name":"ai.theaggregate/the-aggregate","title":"The Aggregate — LLM benchmark aggregate","description":"LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.","version":"1.0.2","websiteUrl":"https://theaggregate.ai/mcp","repositoryUrl":null,"remotes":[{"url":"https://theaggregate.ai/mcp","type":"streamable-http"}],"packages":[],"status":"active","isLatest":true,"publishedAt":"2026-10-09T22:44:57.074Z","updatedAt":"2026-10-09T22:44:57.074Z","source":"official-registry","verification":"official","confidence":100,"stars":null,"sources":[{"stars":null,"title":"The Aggregate — LLM benchmark aggregate","source":"official-registry","sourceId":"ai.theaggregate/the-aggregate","updatedAt":"2026-10-09T22:44:57.074Z","confidence":100,"websiteUrl":"https://theaggregate.ai/mcp","description":"LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.","verification":"official","repositoryUrl":null}],"toolIndex":{"tools":[{"serverName":"ai.theaggregate/the-aggregate","endpointFingerprint":"05b68f917d1da8b2cb8ba42d57c7f368f5fb00db23e842f2a7eef16649456e79","name":"about_the_aggregate","title":"About The Aggregate","description":"What this data is: the published rating method, current coverage counts, update cadence, and how to cite it.","inputSchema":{"type":"object","properties":{}},"annotations":{"title":"About The Aggregate","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"987ba2a8f66475973284ec3c715c24440184900c4c8f265d429c01218bf1e60d","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-14T00:46:33.876Z","metadataTrust":"untrusted"},{"serverName":"ai.theaggregate/the-aggregate","endpointFingerprint":"05b68f917d1da8b2cb8ba42d57c7f368f5fb00db23e842f2a7eef16649456e79","name":"compare_models","title":"Compare models","description":"Head-to-head between 2-4 models: aggregate ranks, rating gap with a significance note based on the standard errors, and notable benchmarks they share.","inputSchema":{"type":"object","properties":{"models":{"type":"array","items":{"type":"string"},"minItems":2,"maxItems":4,"description":"Two to four model names or slugs."}},"required":["models"]},"annotations":{"title":"Compare models","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"39528f8f1a188319502f99ef6ea5dbef4c6eb69fc42d419c7a5c0ebb450dd2d2","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-14T00:46:33.876Z","metadataTrust":"untrusted"},{"serverName":"ai.theaggregate/the-aggregate","endpointFingerprint":"05b68f917d1da8b2cb8ba42d57c7f368f5fb00db23e842f2a7eef16649456e79","name":"get_benchmark","title":"Benchmark detail","description":"One benchmark in depth: what it measures, the original source leaderboard URL, IRT stats (difficulty, noise, model coverage), skill weights, and the current top models on it.","inputSchema":{"type":"object","properties":{"benchmark":{"type":"string","description":"Benchmark name or slug, e.g. \"Aider polyglot\"."},"top":{"type":"number","description":"How many top models to list (1-50, default 10)."}},"required":["benchmark"]},"annotations":{"title":"Benchmark detail","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"d8993bb791a0c27cbf8128103cd110d993cde3266ea7d3d3979305aac15686ae","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-14T00:46:33.876Z","metadataTrust":"untrusted"},{"serverName":"ai.theaggregate/the-aggregate","endpointFingerprint":"05b68f917d1da8b2cb8ba42d57c7f368f5fb00db23e842f2a7eef16649456e79","name":"get_leaderboard","title":"Aggregate leaderboard","description":"Top of the cross-benchmark aggregate ranking: published Aggregate Ratings combine public benchmark evidence on one scale (call about_the_aggregate for the current coverage and method). One row per model by default, fused across reasoning-effort settings. Supports paging via limit/offset.","inputSchema":{"type":"object","properties":{"limit":{"type":"number","description":"Rows to return (1-100, default 25)."},"offset":{"type":"number","description":"Rows to skip from the top (default 0)."},"include_variants":{"type":"boolean","description":"Rank each reasoning-effort variant separately (e.g. \"Claude Opus 4.6 (High)\") instead of one fused row per model. Default false."}}},"annotations":{"title":"Aggregate leaderboard","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"d8c900c325ff2a588a8acf6d3bbdd6c008dd31a45dec48f129bb5f4bfde73d73","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-14T00:46:33.876Z","metadataTrust":"untrusted"},{"serverName":"ai.theaggregate/the-aggregate","endpointFingerprint":"05b68f917d1da8b2cb8ba42d57c7f368f5fb00db23e842f2a7eef16649456e79","name":"get_model","title":"Model profile","description":"One model in depth: aggregate rank, Aggregate Rating with standard error, provider, what it is, cost per task where known, and its most notable benchmark results (with percentiles).","inputSchema":{"type":"object","properties":{"model":{"type":"string","description":"Model name or slug, e.g. \"Claude Opus 4.5\" or \"gpt-5-5\"."}},"required":["model"]},"annotations":{"title":"Model profile","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"48ee94387456c5eab0c4740807c6dcb18a5e0b55a0152b54c56ef3fc59cd18a9","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-14T00:46:33.876Z","metadataTrust":"untrusted"},{"serverName":"ai.theaggregate/the-aggregate","endpointFingerprint":"05b68f917d1da8b2cb8ba42d57c7f368f5fb00db23e842f2a7eef16649456e79","name":"get_prediction_duel","title":"Prediction duel standings","description":"Guesswork — the public prediction duel: every day frontier LLMs and The Aggregate's own IRT model predict newly scraped benchmark scores before seeing them, and the errors are scored. Returns the current monthly standings, wins and losses included.","inputSchema":{"type":"object","properties":{}},"annotations":{"title":"Prediction duel standings","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"103a350699fdac8c078b7cf7df0c54ca86a763ff146763b95411f230e98ff469","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-14T00:46:33.876Z","metadataTrust":"untrusted"},{"serverName":"ai.theaggregate/the-aggregate","endpointFingerprint":"05b68f917d1da8b2cb8ba42d57c7f368f5fb00db23e842f2a7eef16649456e79","name":"search_benchmarks","title":"Search benchmarks","description":"Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the rating scale, and the benchmark page URL.","inputSchema":{"type":"object","properties":{"query":{"type":"string","description":"Benchmark name fragment, e.g. \"swe-bench\" or \"arena\"."},"limit":{"type":"number","description":"Max results (1-25, default 10)."}},"required":["query"]},"annotations":{"title":"Search benchmarks","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"0ec1e92183afd57e285488d1b1a69ce3ac4691611cecb705fbec316baa0838dd","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-14T00:46:33.876Z","metadataTrust":"untrusted"},{"serverName":"ai.theaggregate/the-aggregate","endpointFingerprint":"05b68f917d1da8b2cb8ba42d57c7f368f5fb00db23e842f2a7eef16649456e79","name":"search_models","title":"Search models","description":"Find ranked models by (partial) name or provider. Returns rank, Aggregate Rating and the model page URL. One row per model by default, fused across reasoning-effort settings.","inputSchema":{"type":"object","properties":{"query":{"type":"string","description":"Model or provider name fragment, e.g. \"opus\" or \"deepseek\"."},"limit":{"type":"number","description":"Max results (1-25, default 10)."},"include_variants":{"type":"boolean","description":"Return each reasoning-effort variant separately (e.g. \"Claude Opus 4.6 (High)\") instead of one fused row per model. Default false."}},"required":["query"]},"annotations":{"title":"Search models","readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false},"definitionHash":"8853ff0003296138af10be89279665aefdcd0a86199ea041261501f68e6c7390","schemaStatus":"valid","origin":"official-registry","observedAt":"2026-11-14T00:46:33.876Z","metadataTrust":"untrusted"}],"endpoints":[{"endpointFingerprint":"05b68f917d1da8b2cb8ba42d57c7f368f5fb00db23e842f2a7eef16649456e79","protocol":"streamable-http","status":"indexed","toolCount":8,"observedAt":"2026-11-14T00:46:33.876Z"}],"authentication":"unknown"},"connectionConfigurations":{"status":"ready","authentication":"not embedded","clients":{"Claude Desktop":{"mcpServers":{"ai.theaggregate/the-aggregate":{"url":"https://theaggregate.ai/mcp"}}},"Cursor":{"mcpServers":{"ai.theaggregate/the-aggregate":{"url":"https://theaggregate.ai/mcp"}}},"VS Code":{"servers":{"ai.theaggregate/the-aggregate":{"type":"http","url":"https://theaggregate.ai/mcp"}}}}},"resourceType":"mcp-server","callable":true,"runtime":{"callable":true,"protocols":["mcp"]},"interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://theaggregate.ai/mcp"}],"profile":{"apiVersion":"1","schemaVersion":"1","id":"mcp-server:ai.theaggregate%2Fthe-aggregate","resourceType":"mcp-server","canonicalUrl":"https://www.agentsjunction.com/api/v1/servers/ai.theaggregate%2Fthe-aggregate","name":"ai.theaggregate/the-aggregate","description":"LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.","interfaces":[{"protocol":"mcp","transport":"streamable-http","url":"https://theaggregate.ai/mcp"}],"capabilities":[],"identity":{"source":"official-registry","websiteUrl":"https://theaggregate.ai/mcp","repositoryUrl":null,"version":"1.0.2"},"verification":{"state":"official","confidence":100},"operations":{"resourceType":"mcp-server","name":"ai.theaggregate/the-aggregate","status":"online","lastCheckedAt":"2026-11-20T05:17:09.367Z","lastSuccessfulCheck":"2026-11-20T05:17:09.367Z","latencyMs":86,"consecutiveFailures":0,"isStale":false,"checks":{"endpointReachable":true,"protocolValid":true,"agentCardValid":null,"mcpHandshakeValid":true},"lastSeen":null,"lastSuccessfulInteraction":null,"lastHealthCheck":"2026-11-20T05:17:09.367Z","source":{"type":"health-check","url":null},"observedAt":"2026-11-20T05:17:09.367Z"},"security":null,"timestamps":{"createdAt":"2026-10-09T22:44:57.074Z","updatedAt":"2026-10-09T22:44:57.074Z","observedAt":"2026-11-20T05:17:09.367Z"},"compatibility":{"serverVersion":"1.0.2","protocolVersions":[{"protocol":"mcp","version":null}]}}}}