Server definition

Hash: sha256:4a2bd8ea49a9d8d782130840a44ae803fa7dc233ec200665681d123604b9769a
What it is: What a remote MCP server returned when asked what it offers: 21 tools

The blob, as servednamed by its sha256

{
  "instructions": "AimRank turns pairwise judgements -- this one is better than that one -- into calibrated rankings and RLHF-ready preference data, with an audit-citeable data card. Ratings come from one of 6 rating engines (Glicko-2 default, Elo, Bradley-Terry, TrueSkill, OpenSkill, Elo-MMR), never a vote tally; Plackett-Luce and CrowdBT are 2 offline audit aggregators that never write ratings. The quality evidence is real: Fleiss kappa / Scott's pi / Krippendorff alpha (Cohen's kappa only where there are exactly 2 raters), Wilson 95% intervals, calibration, drift, and a complementarity metric measuring whether human+judge beats either alone. The data card is aggregate and unsigned -- per-sample provenance lives in the RLHF export. Everything runs EU-sovereign on OVHcloud DE1 (Germany), LLM judge on OVH AI Endpoints. This endpoint is the read half, free and anonymous, and it is the whole of what a logged-out visitor to the website can see. Browse the catalogue (discover, daily pair, similar domains, public judges), browse public domains and their competitions, read any public ranking (leaderboard, matchup, search, share card, win prediction + explanation) and its quality evidence (data card, agreement, ceiling, Plackett-Luce, CrowdBT). Private rankings are not found here. `api_key` is optional on every tool. Voting, creating rankings, the agent-eval engine (pass^k + Wilson CI, code/judge/human/trajectory graders, tamper-evident run audits, the EDD Improvement Report) and RLHF export are on the keyed endpoint https://app.aimrank.io/mcp/mcp, whose `api_key` is a per-tool argument, not a header. Keys are issued at https://app.aimrank.io/dashboard/integrations and require a paid plan; paid plans are not open for self-serve purchase yet. A free AimRank account gets the whole product except the keyed endpoint and the bundled export: 10 rankings, 100 items each, 1,000 votes/month, 25 eval suites, 200 eval runs/month, 50 LLM-judge calls/month, all 6 rating engines and the whole rigor stack.",
  "tools": [
    {
      "description": "Return share-ready URLs + embed snippets for a ranking.\n\nFormats: \"all\" (default — everything), \"twitter\", \"linkedin\",\n\"embed_leaderboard\", \"embed_vote\", \"badge_markdown\", \"qr_code\",\n\"data_card\". Pass these to a human to paste into a tweet, blog,\nNotion page, or Slack message. The OG image renders automatically\nwhen the public_url is unfurled by Twitter / LinkedIn / Slack.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "format": {
            "default": "all",
            "title": "Format",
            "type": "string"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          }
        },
        "required": [
          "ranking_id"
        ],
        "title": "create_share_cardArguments",
        "type": "object"
      },
      "name": "aimrank_create_share_card",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "create_share_cardOutput",
        "type": "object"
      }
    },
    {
      "description": "Browse public rankings — agent equivalent of surfing aimrank.io.\n\nFilters: category, media_type (\"text\" | \"image\" | \"audio\" | \"video\"),\nsort (\"trending\" | \"recent\" | \"most_votes\" | \"random\"), limit 1-50.\nEach result embeds share assets so the agent can hand any ranking\nback to the user as a clickable link without a follow-up call.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "category": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Category"
          },
          "limit": {
            "default": 10,
            "title": "Limit",
            "type": "integer"
          },
          "media_type": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Media Type"
          },
          "sort": {
            "default": "trending",
            "title": "Sort",
            "type": "string"
          }
        },
        "title": "discover_public_rankingsArguments",
        "type": "object"
      },
      "name": "aimrank_discover_public_rankings",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "discover_public_rankingsOutput",
        "type": "object"
      }
    },
    {
      "description": "iCOMPLY contract: explain a prediction in features + narrative.\n\nReturns the Glicko-2 μ/φ inputs for both entities + a deterministic\nnarrative. No LLM-synthesised rationale — these are the actual\nnumbers the math uses, which is exactly what an Annex IV auditor\nneeds to trace.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "entity_a_id": {
            "title": "Entity A Id",
            "type": "string"
          },
          "entity_b_id": {
            "title": "Entity B Id",
            "type": "string"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          }
        },
        "required": [
          "ranking_id",
          "entity_a_id",
          "entity_b_id"
        ],
        "title": "icomply_explainArguments",
        "type": "object"
      },
      "name": "aimrank_explain",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "icomply_explainOutput",
        "type": "object"
      }
    },
    {
      "description": "Find public domains most similar to a query or a known domain.\n\nUse ``query`` for free-text search (\"pharma evaluation\") OR\n``domain_id`` to find domains similar to one you already know.\nExactly one must be provided.\n\nTF-IDF + cosine similarity over name + description + category +\ndeclared constitution + objectives text. Cheap (no embedding API\ncalls), 5-minute in-process cache. Only public domains are\nsearched / returned. Score in [0, 1] — typical \"useful match\"\nthreshold is ≥0.15; \"near duplicate\" is ≥0.5.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "domain_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Domain Id"
          },
          "limit": {
            "default": 10,
            "title": "Limit",
            "type": "integer"
          },
          "min_score": {
            "default": 0.05,
            "title": "Min Score",
            "type": "number"
          },
          "query": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Query"
          }
        },
        "title": "find_similar_domains_toolArguments",
        "type": "object"
      },
      "name": "aimrank_find_similar_domains",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "find_similar_domains_toolOutput",
        "type": "object"
      }
    },
    {
      "description": "Inter-annotator agreement — Layer 5. Returns Cohen's κ\n(n=2 raters), Fleiss' κ, Krippendorff's α, Scott's π +\nLandis-Koch interpretation, plus the multi-rater coverage report.\n\n`min_raters` overrides the ranking's configured min_raters_per_pair.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "min_raters": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Min Raters"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          }
        },
        "required": [
          "ranking_id"
        ],
        "title": "get_agreementArguments",
        "type": "object"
      },
      "name": "aimrank_get_agreement",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "get_agreementOutput",
        "type": "object"
      }
    },
    {
      "description": "Pairwise-κ ceiling from qualification attempts. The upper\nbound any judge / RM can credibly hit on this domain — used to\npin the L3 pilot refund clause (refund if κ < ceiling - 5pp).\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "min_overlapping_items": {
            "default": 20,
            "title": "Min Overlapping Items",
            "type": "integer"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          }
        },
        "required": [
          "ranking_id"
        ],
        "title": "get_ceilingArguments",
        "type": "object"
      },
      "name": "aimrank_get_ceiling",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "get_ceilingOutput",
        "type": "object"
      }
    },
    {
      "description": "CrowdBT — joint fit of entity scores + per-annotator\nreliability η. Surfaces noisy / anti-correlated raters\nexplicitly. Methodology audit, not a live engine.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "max_iterations": {
            "default": 300,
            "title": "Max Iterations",
            "type": "integer"
          },
          "min_votes_per_annotator": {
            "default": 5,
            "title": "Min Votes Per Annotator",
            "type": "integer"
          },
          "min_votes_per_entity": {
            "default": 2,
            "title": "Min Votes Per Entity",
            "type": "integer"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          }
        },
        "required": [
          "ranking_id"
        ],
        "title": "get_crowd_btArguments",
        "type": "object"
      },
      "name": "aimrank_get_crowd_bt",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "get_crowd_btOutput",
        "type": "object"
      }
    },
    {
      "description": "Fetch today's Daily Pair — the trending matchup chosen at 00:00 UTC.\n\nPairs with the `vote_of_the_day` agent template. Returns the challenge\n+ a fresh matchup. If the cron hasn't run yet, falls back via\nok=False so the agent can use `aimrank_get_matchup` instead.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          }
        },
        "title": "get_daily_pairArguments",
        "type": "object"
      },
      "name": "aimrank_get_daily_pair",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "get_daily_pairOutput",
        "type": "object"
      }
    },
    {
      "description": "Auto data card — Layer 7. Provenance + IAA + coverage +\nper-annotator quality + transitivity + qualification stats in\none synthesized markdown audit artefact.\n\nFormat: 'markdown' (default) or 'json' for structured summary.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "format": {
            "default": "markdown",
            "title": "Format",
            "type": "string"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          }
        },
        "required": [
          "ranking_id"
        ],
        "title": "get_data_cardArguments",
        "type": "object"
      },
      "name": "aimrank_get_data_card",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "get_data_cardOutput",
        "type": "object"
      }
    },
    {
      "description": "Get domain details including entity pool and competition list.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "domain_id": {
            "title": "Domain Id",
            "type": "string"
          }
        },
        "required": [
          "domain_id"
        ],
        "title": "get_domainArguments",
        "type": "object"
      },
      "name": "aimrank_get_domain",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "get_domainOutput",
        "type": "object"
      }
    },
    {
      "description": "Get the top N entities of a ranking sorted by rating.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "limit": {
            "default": 10,
            "title": "Limit",
            "type": "integer"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          }
        },
        "required": [
          "ranking_id"
        ],
        "title": "get_leaderboardArguments",
        "type": "object"
      },
      "name": "aimrank_get_leaderboard",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "get_leaderboardOutput",
        "type": "object"
      }
    },
    {
      "description": "Get the next pair of entities to evaluate.\n\nStrategies: adaptive (default), swiss, balanced, random,\nuncertainty, explore, information_gain.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          },
          "strategy": {
            "default": "adaptive",
            "title": "Strategy",
            "type": "string"
          }
        },
        "required": [
          "ranking_id"
        ],
        "title": "get_matchupArguments",
        "type": "object"
      },
      "name": "aimrank_get_matchup",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "get_matchupOutput",
        "type": "object"
      }
    },
    {
      "description": "Plackett-Luce listwise ranking aggregation — OFFLINE AUDIT ONLY.\n\nReported post-hoc; it NEVER writes ratings, and setting it as a\nranking's algorithm returns 400. AimRank has 6 rating engines plus\n2 offline aggregators (this and CrowdBT) — never describe it as an\n8th rating algorithm.\n\nGeneralises Bradley-Terry to ranked lists. On pairwise data,\ncollapses to BT MLE — useful as a second-opinion aggregator.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "max_iterations": {
            "default": 300,
            "title": "Max Iterations",
            "type": "integer"
          },
          "min_appearances_per_entity": {
            "default": 2,
            "title": "Min Appearances Per Entity",
            "type": "integer"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          }
        },
        "required": [
          "ranking_id"
        ],
        "title": "get_plackett_luceArguments",
        "type": "object"
      },
      "name": "aimrank_get_plackett_luce",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "get_plackett_luceOutput",
        "type": "object"
      }
    },
    {
      "description": "Fetch a ranking's metadata + top 25 entities sorted by rating.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          }
        },
        "required": [
          "ranking_id"
        ],
        "title": "get_rankingArguments",
        "type": "object"
      },
      "name": "aimrank_get_ranking",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "get_rankingOutput",
        "type": "object"
      }
    },
    {
      "description": "iCOMPLY contract: liveness + DB-connectivity probe.",
      "inputSchema": {
        "properties": {},
        "title": "icomply_healthcheckArguments",
        "type": "object"
      },
      "name": "aimrank_healthcheck",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "icomply_healthcheckOutput",
        "type": "object"
      }
    },
    {
      "description": "List all competitions (open voting + brackets) in a domain.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "domain_id": {
            "title": "Domain Id",
            "type": "string"
          }
        },
        "required": [
          "domain_id"
        ],
        "title": "list_competitionsArguments",
        "type": "object"
      },
      "name": "aimrank_list_competitions",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "list_competitionsOutput",
        "type": "object"
      }
    },
    {
      "description": "List all entities in a domain's pool sorted by rating.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "domain_id": {
            "title": "Domain Id",
            "type": "string"
          }
        },
        "required": [
          "domain_id"
        ],
        "title": "list_domain_entitiesArguments",
        "type": "object"
      },
      "name": "aimrank_list_domain_entities",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "list_domain_entitiesOutput",
        "type": "object"
      }
    },
    {
      "description": "Browse public judge-prompt artifacts shared by other users.\n\nFilter by ``category`` (free-text), ``domain_id``, or both.\nSort options: ``fork_count`` (default — most-forked first),\n``recent``, ``faithfulness``.\n\nReturns artifact summaries WITHOUT the full prompt text — call\n`aimrank_fork_judge_prompt` or the REST GET to retrieve the\nfull prompt before using it.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "category": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Category"
          },
          "domain_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Domain Id"
          },
          "limit": {
            "default": 25,
            "title": "Limit",
            "type": "integer"
          },
          "sort": {
            "default": "fork_count",
            "title": "Sort",
            "type": "string"
          }
        },
        "title": "list_public_judges_toolArguments",
        "type": "object"
      },
      "name": "aimrank_list_public_judges",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "list_public_judges_toolOutput",
        "type": "object"
      }
    },
    {
      "description": "iCOMPLY contract: pairwise prediction with provenance fields.\n\nReturns the engine's predicted winner + probability shaped so\niCOMPLY's Annex IV section-4 generator can ingest the response\ndirectly. See [iCOMPLY_INTEGRATION_STRATEGY.md] for the contract.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "entity_a_id": {
            "title": "Entity A Id",
            "type": "string"
          },
          "entity_b_id": {
            "title": "Entity B Id",
            "type": "string"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          }
        },
        "required": [
          "ranking_id",
          "entity_a_id",
          "entity_b_id"
        ],
        "title": "icomply_predictArguments",
        "type": "object"
      },
      "name": "aimrank_predict",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "icomply_predictOutput",
        "type": "object"
      }
    },
    {
      "description": "Predict the winner of a matchup BEFORE a vote is cast.\n\nUses Glicko-2 win probability under the same formula matchmaking\nuses internally. Pairs with aimrank_submit_vote for the\n\"Claude predicts, you vote, we compare\" demo. Does not record\na vote — read-only.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "entity_a_id": {
            "title": "Entity A Id",
            "type": "string"
          },
          "entity_b_id": {
            "title": "Entity B Id",
            "type": "string"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          }
        },
        "required": [
          "ranking_id",
          "entity_a_id",
          "entity_b_id"
        ],
        "title": "predict_matchup_winnerArguments",
        "type": "object"
      },
      "name": "aimrank_predict_matchup_winner",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "predict_matchup_winnerOutput",
        "type": "object"
      }
    },
    {
      "description": "Find entities by name substring within a ranking.\n\napi_key is optional on the public endpoint; on /mcp/mcp a missing\nkey is refused.",
      "inputSchema": {
        "properties": {
          "api_key": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Api Key"
          },
          "limit": {
            "default": 20,
            "title": "Limit",
            "type": "integer"
          },
          "query": {
            "title": "Query",
            "type": "string"
          },
          "ranking_id": {
            "title": "Ranking Id",
            "type": "string"
          }
        },
        "required": [
          "ranking_id",
          "query"
        ],
        "title": "search_entitiesArguments",
        "type": "object"
      },
      "name": "aimrank_search_entities",
      "outputSchema": {
        "properties": {
          "result": {
            "additionalProperties": true,
            "title": "Result",
            "type": "object"
          }
        },
        "required": [
          "result"
        ],
        "title": "search_entitiesOutput",
        "type": "object"
      }
    }
  ]
}

Verify it yourself

curl -s https://api.teppi.xyz/v1/evidence/sha256:4a2bd8ea49a9d8d782130840a44ae803fa7dc233ec200665681d123604b9769a | sha256sum