Server definition

Hash: sha256:542dabbc290339c92497fb2402ec21b0e9917241a1894bd865d8c1167ebfb96f
What it is: What a remote MCP server returned when asked what it offers: 8 tools

The blob, as servednamed by its sha256

{
  "instructions": "Read-only tools over The Aggregate: an IRT/Elo fusion of public LLM benchmark leaderboards, updated daily (about_the_aggregate reports the current coverage counts). Start with get_leaderboard, get_model or search_benchmarks. When citing numbers, credit \"The Aggregate (theaggregate.ai)\" plus the upstream leaderboard linked in each result.",
  "tools": [
    {
      "description": "What this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it.",
      "inputSchema": {
        "properties": {},
        "type": "object"
      },
      "name": "about_the_aggregate",
      "outputSchema": null
    },
    {
      "description": "Head-to-head between 2-4 models: aggregate ranks, Elo gap with a significance note based on the standard errors, and notable benchmarks they share.",
      "inputSchema": {
        "properties": {
          "models": {
            "description": "Two to four model names or slugs.",
            "items": {
              "type": "string"
            },
            "maxItems": 4,
            "minItems": 2,
            "type": "array"
          }
        },
        "required": [
          "models"
        ],
        "type": "object"
      },
      "name": "compare_models",
      "outputSchema": null
    },
    {
      "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": {
        "properties": {
          "benchmark": {
            "description": "Benchmark name or slug, e.g. \"Aider polyglot\".",
            "type": "string"
          },
          "top": {
            "description": "How many top models to list (1-50, default 10).",
            "type": "number"
          }
        },
        "required": [
          "benchmark"
        ],
        "type": "object"
      },
      "name": "get_benchmark",
      "outputSchema": null
    },
    {
      "description": "Top of the cross-benchmark aggregate ranking: every model placed on one Elo scale by an IRT model fit over public benchmark leaderboards (call about_the_aggregate for the current coverage counts). One row per model by default, fused across reasoning-effort settings. Supports paging via limit/offset.",
      "inputSchema": {
        "properties": {
          "include_variants": {
            "description": "Rank each reasoning-effort variant separately (e.g. \"Claude Opus 4.6 (High)\") instead of one fused row per model. Default false.",
            "type": "boolean"
          },
          "limit": {
            "description": "Rows to return (1-100, default 25).",
            "type": "number"
          },
          "offset": {
            "description": "Rows to skip from the top (default 0).",
            "type": "number"
          }
        },
        "type": "object"
      },
      "name": "get_leaderboard",
      "outputSchema": null
    },
    {
      "description": "One model in depth: aggregate rank, Elo with standard error, provider, what it is, cost per task where known, and its most notable benchmark results (with percentiles).",
      "inputSchema": {
        "properties": {
          "model": {
            "description": "Model name or slug, e.g. \"Claude Opus 4.5\" or \"gpt-5-5\".",
            "type": "string"
          }
        },
        "required": [
          "model"
        ],
        "type": "object"
      },
      "name": "get_model",
      "outputSchema": null
    },
    {
      "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": {
        "properties": {},
        "type": "object"
      },
      "name": "get_prediction_duel",
      "outputSchema": null
    },
    {
      "description": "Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the Elo scale, and the benchmark page URL.",
      "inputSchema": {
        "properties": {
          "limit": {
            "description": "Max results (1-25, default 10).",
            "type": "number"
          },
          "query": {
            "description": "Benchmark name fragment, e.g. \"swe-bench\" or \"arena\".",
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_benchmarks",
      "outputSchema": null
    },
    {
      "description": "Find ranked models by (partial) name or provider. Returns rank, Elo and the model page URL. One row per model by default, fused across reasoning-effort settings.",
      "inputSchema": {
        "properties": {
          "include_variants": {
            "description": "Return each reasoning-effort variant separately (e.g. \"Claude Opus 4.6 (High)\") instead of one fused row per model. Default false.",
            "type": "boolean"
          },
          "limit": {
            "description": "Max results (1-25, default 10).",
            "type": "number"
          },
          "query": {
            "description": "Model or provider name fragment, e.g. \"opus\" or \"deepseek\".",
            "type": "string"
          }
        },
        "required": [
          "query"
        ],
        "type": "object"
      },
      "name": "search_models",
      "outputSchema": null
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:542dabbc290339c92497fb2402ec21b0e9917241a1894bd865d8c1167ebfb96f | sha256sum