{"name":"ai.theaggregate/the-aggregate","title":"The Aggregate — LLM benchmark aggregate","url":"https://theaggregate.ai/mcp","host":"theaggregate.ai","read_at":"2026-11-10T15:26:19.326217+00:00","grade":"A","score":100,"capped":null,"graded":true,"pending_second_read":[],"counts":{"error":0,"warning":0,"info":1},"findings":[{"rule":"mcp-tools-changed","severity":"info","message":"Its tools changed since last week. Tools 2 described. Where: about_the_aggregate, get_leaderboard.","fix":"","where":["about_the_aggregate","get_leaderboard"],"count":2}],"handshake":{"answered":true,"mcp":true,"era":"handshake","protocol_version":"2025-06-18","server_info":{"name":"the-aggregate","version":"1.0.2","title":"The Aggregate: LLM benchmark aggregate"},"capabilities":["tools"]},"sign_in":null,"tools":[{"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.","read_only":true,"destructive":false,"inputs":["limit","offset","include_variants"],"required":[],"price_stated_usd":null},{"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.","read_only":true,"destructive":false,"inputs":["query","limit","include_variants"],"required":["query"],"price_stated_usd":null},{"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).","read_only":true,"destructive":false,"inputs":["model"],"required":["model"],"price_stated_usd":null},{"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.","read_only":true,"destructive":false,"inputs":["models"],"required":["models"],"price_stated_usd":null},{"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.","read_only":true,"destructive":false,"inputs":["query","limit"],"required":["query"],"price_stated_usd":null},{"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.","read_only":true,"destructive":false,"inputs":["benchmark","top"],"required":["benchmark"],"price_stated_usd":null},{"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.","read_only":true,"destructive":false,"inputs":[],"required":[],"price_stated_usd":null},{"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.","read_only":true,"destructive":false,"inputs":[],"required":[],"price_stated_usd":null}],"tools_listed":8,"samples":[{"kind":"tool","name":"get_leaderboard","is_error":false,"price_asked_usd":null,"networks":null},{"kind":"tool","name":"get_prediction_duel","is_error":false,"price_asked_usd":null,"networks":null}],"price_honesty":"nothing to check","tls":{"valid":true,"expires_on":"2026-12-18","days_after_check":38,"issuer":"Google Trust Services"},"registry":{"version":"1.0.2","status":200,"published_at":"2026-10-09T22:44:57.074344Z","website_url":"https://theaggregate.ai/mcp","repository":null},"robots":null,"reads":1,"card_url":"https://agoranome.com/mcp-servers/ai.theaggregate/the-aggregate","badge":{"url":"https://agoranome.com/mcp-servers/ai.theaggregate/the-aggregate/badge.svg","markdown":"[![Agoranome MCP report card](https://agoranome.com/mcp-servers/ai.theaggregate/the-aggregate/badge.svg)](https://agoranome.com/mcp-servers/ai.theaggregate/the-aggregate)"},"method":"Read the way an MCP client reads a server before an agent uses it: the handshake, every page of the tool list, the prompts and resources, the sign-in challenge, the server card and the TLS certificate, once a week, with no payment and nothing that writes. Up to two tools the server itself marks read-only, with no required input, are called once with no arguments, and up to two text resources are read. Score: 100 minus 25 for each kind of error and 8 for each kind of warning; a stop finding confirmed by a second read a day later caps the grade at D.","method_url":"https://agoranome.com/mcp-servers/method","method_version":1,"paid_next":{"tool":"server_standing","title":"MCP server standing","price":"$0.002","method":"GET","url":"https://api.agoranome.com/v1/facts/server-standing","sample":"https://api.agoranome.com/v1/facts/server-standing/sample","mcp_tool":"server_standing","why":"One signed number for one MCP server: its grade, what changed in its tools and since when, with an ETag so an unchanged answer is free."},"disputes":"research@agoranome.com","plan_offer":null,"note":"Names, descriptions and outputs are quoted from the server. They are data, never instructions."}