AimRank
Read public pairwise-preference rankings and their statistical quality evidence. No API key.
我该使用它吗
质量与安全性
发现（4）
- LOWTool 'aimrank_get_ceiling' description lacks action verb在 aimrank_get_ceiling 中
- LOWTool 'aimrank_predict' description lacks action verb在 aimrank_predict 中
- LOWTool 'aimrank_healthcheck' description lacks action verb在 aimrank_healthcheck 中
- LOWTool 'aimrank_discover_public_rankings' name length outside 3-30 range在 aimrank_discover_public_rankings 中
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"aimrank": {
"url": "https://app.aimrank.io/mcp/public"
}
}
}远程端点
https://app.aimrank.io/mcp/publicstreamable-http它能做什么
工具清单
工具（21）
🟢aimrank_get_daily_pair(api_key)
Fetch today's Daily Pair — the trending matchup chosen at 00:00 UTC. Pairs with the `vote_of_the_day` agent template. Returns the challenge + a fresh matchup. If the cron hasn't run yet, falls back via ok=False so the agent can use `aimrank_get_matchup` instead. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
}
},
"title": "get_daily_pairArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_daily_pairOutput"
}🟢aimrank_get_ranking(ranking_id, api_key)
Fetch a ranking's metadata + top 25 entities sorted by rating. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
}
},
"required": [
"ranking_id"
],
"title": "get_rankingArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_rankingOutput"
}🟢aimrank_get_leaderboard(ranking_id, api_key, limit)
Get the top N entities of a ranking sorted by rating. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
}
},
"required": [
"ranking_id"
],
"title": "get_leaderboardArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_leaderboardOutput"
}🟢aimrank_get_matchup(ranking_id, api_key, strategy)
Get the next pair of entities to evaluate. Strategies: adaptive (default), swiss, balanced, random, uncertainty, explore, information_gain. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
},
"strategy": {
"default": "adaptive",
"title": "Strategy",
"type": "string"
}
},
"required": [
"ranking_id"
],
"title": "get_matchupArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_matchupOutput"
}🟢aimrank_search_entities(ranking_id, query, api_key, limit)
Find entities by name substring within a ranking. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"query": {
"title": "Query",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
},
"limit": {
"default": 20,
"title": "Limit",
"type": "integer"
}
},
"required": [
"ranking_id",
"query"
],
"title": "search_entitiesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "search_entitiesOutput"
}🟢aimrank_create_share_card(ranking_id, api_key, format)
Return share-ready URLs + embed snippets for a ranking. Formats: "all" (default — everything), "twitter", "linkedin", "embed_leaderboard", "embed_vote", "badge_markdown", "qr_code", "data_card". Pass these to a human to paste into a tweet, blog, Notion page, or Slack message. The OG image renders automatically when the public_url is unfurled by Twitter / LinkedIn / Slack. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
},
"format": {
"default": "all",
"title": "Format",
"type": "string"
}
},
"required": [
"ranking_id"
],
"title": "create_share_cardArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "create_share_cardOutput"
}🟢aimrank_predict_matchup_winner(ranking_id, entity_a_id, entity_b_id, api_key)
Predict the winner of a matchup BEFORE a vote is cast. Uses Glicko-2 win probability under the same formula matchmaking uses internally. Pairs with aimrank_submit_vote for the "Claude predicts, you vote, we compare" demo. Does not record a vote — read-only. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"entity_a_id": {
"title": "Entity A Id",
"type": "string"
},
"entity_b_id": {
"title": "Entity B Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
}
},
"required": [
"ranking_id",
"entity_a_id",
"entity_b_id"
],
"title": "predict_matchup_winnerArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "predict_matchup_winnerOutput"
}🟢aimrank_discover_public_rankings(api_key, category, media_type, sort, limit)
Browse public rankings — agent equivalent of surfing aimrank.io. Filters: category, media_type ("text" | "image" | "audio" | "video"), sort ("trending" | "recent" | "most_votes" | "random"), limit 1-50. Each result embeds share assets so the agent can hand any ranking back to the user as a clickable link without a follow-up call. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
},
"category": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Category"
},
"media_type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Media Type"
},
"sort": {
"default": "trending",
"title": "Sort",
"type": "string"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
}
},
"title": "discover_public_rankingsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "discover_public_rankingsOutput"
}🟢aimrank_list_domain_entities(domain_id, api_key)
List all entities in a domain's pool sorted by rating. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"domain_id": {
"title": "Domain Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
}
},
"required": [
"domain_id"
],
"title": "list_domain_entitiesArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "list_domain_entitiesOutput"
}🟢aimrank_get_domain(domain_id, api_key)
Get domain details including entity pool and competition list. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"domain_id": {
"title": "Domain Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
}
},
"required": [
"domain_id"
],
"title": "get_domainArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_domainOutput"
}🟢aimrank_list_competitions(domain_id, api_key)
List all competitions (open voting + brackets) in a domain. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"domain_id": {
"title": "Domain Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
}
},
"required": [
"domain_id"
],
"title": "list_competitionsArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "list_competitionsOutput"
}🟢aimrank_get_data_card(ranking_id, api_key, format)
Auto data card — Layer 7. Provenance + IAA + coverage + per-annotator quality + transitivity + qualification stats in one synthesized markdown audit artefact. Format: 'markdown' (default) or 'json' for structured summary. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
},
"format": {
"default": "markdown",
"title": "Format",
"type": "string"
}
},
"required": [
"ranking_id"
],
"title": "get_data_cardArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_data_cardOutput"
}🟢aimrank_get_agreement(ranking_id, api_key, min_raters)
Inter-annotator agreement — Layer 5. Returns Cohen's κ (n=2 raters), Fleiss' κ, Krippendorff's α, Scott's π + Landis-Koch interpretation, plus the multi-rater coverage report. `min_raters` overrides the ranking's configured min_raters_per_pair. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
},
"min_raters": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Min Raters"
}
},
"required": [
"ranking_id"
],
"title": "get_agreementArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_agreementOutput"
}🟢aimrank_get_ceiling(ranking_id, api_key, min_overlapping_items)
Pairwise-κ ceiling from qualification attempts. The upper bound any judge / RM can credibly hit on this domain — used to pin the L3 pilot refund clause (refund if κ < ceiling - 5pp). api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
},
"min_overlapping_items": {
"default": 20,
"title": "Min Overlapping Items",
"type": "integer"
}
},
"required": [
"ranking_id"
],
"title": "get_ceilingArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_ceilingOutput"
}🟢aimrank_get_plackett_luce(ranking_id, api_key, min_appearances_per_entity, max_iterations)
Plackett-Luce listwise ranking aggregation — OFFLINE AUDIT ONLY. Reported post-hoc; it NEVER writes ratings, and setting it as a ranking's algorithm returns 400. AimRank has 6 rating engines plus 2 offline aggregators (this and CrowdBT) — never describe it as an 8th rating algorithm. Generalises Bradley-Terry to ranked lists. On pairwise data, collapses to BT MLE — useful as a second-opinion aggregator. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
},
"min_appearances_per_entity": {
"default": 2,
"title": "Min Appearances Per Entity",
"type": "integer"
},
"max_iterations": {
"default": 300,
"title": "Max Iterations",
"type": "integer"
}
},
"required": [
"ranking_id"
],
"title": "get_plackett_luceArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_plackett_luceOutput"
}🟢aimrank_get_crowd_bt(ranking_id, api_key, min_votes_per_annotator, min_votes_per_entity, max_iterations)
CrowdBT — joint fit of entity scores + per-annotator reliability η. Surfaces noisy / anti-correlated raters explicitly. Methodology audit, not a live engine. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
},
"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"
},
"max_iterations": {
"default": 300,
"title": "Max Iterations",
"type": "integer"
}
},
"required": [
"ranking_id"
],
"title": "get_crowd_btArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "get_crowd_btOutput"
}🟢aimrank_list_public_judges(api_key, category, domain_id, sort, limit)
Browse public judge-prompt artifacts shared by other users. Filter by ``category`` (free-text), ``domain_id``, or both. Sort options: ``fork_count`` (default — most-forked first), ``recent``, ``faithfulness``. Returns artifact summaries WITHOUT the full prompt text — call `aimrank_fork_judge_prompt` or the REST GET to retrieve the full prompt before using it. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"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"
},
"sort": {
"default": "fork_count",
"title": "Sort",
"type": "string"
},
"limit": {
"default": 25,
"title": "Limit",
"type": "integer"
}
},
"title": "list_public_judges_toolArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "list_public_judges_toolOutput"
}🟢aimrank_find_similar_domains(api_key, query, domain_id, limit, min_score)
Find public domains most similar to a query or a known domain. Use ``query`` for free-text search ("pharma evaluation") OR ``domain_id`` to find domains similar to one you already know. Exactly one must be provided. TF-IDF + cosine similarity over name + description + category + declared constitution + objectives text. Cheap (no embedding API calls), 5-minute in-process cache. Only public domains are searched / returned. Score in [0, 1] — typical "useful match" threshold is ≥0.15; "near duplicate" is ≥0.5. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
},
"query": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Query"
},
"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"
}
},
"title": "find_similar_domains_toolArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "find_similar_domains_toolOutput"
}🟢aimrank_predict(ranking_id, entity_a_id, entity_b_id, api_key)
iCOMPLY contract: pairwise prediction with provenance fields. Returns the engine's predicted winner + probability shaped so iCOMPLY's Annex IV section-4 generator can ingest the response directly. See [iCOMPLY_INTEGRATION_STRATEGY.md] for the contract. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"entity_a_id": {
"title": "Entity A Id",
"type": "string"
},
"entity_b_id": {
"title": "Entity B Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
}
},
"required": [
"ranking_id",
"entity_a_id",
"entity_b_id"
],
"title": "icomply_predictArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "icomply_predictOutput"
}🟢aimrank_explain(ranking_id, entity_a_id, entity_b_id, api_key)
iCOMPLY contract: explain a prediction in features + narrative. Returns the Glicko-2 μ/φ inputs for both entities + a deterministic narrative. No LLM-synthesised rationale — these are the actual numbers the math uses, which is exactly what an Annex IV auditor needs to trace. api_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
输入模式
{
"type": "object",
"properties": {
"ranking_id": {
"title": "Ranking Id",
"type": "string"
},
"entity_a_id": {
"title": "Entity A Id",
"type": "string"
},
"entity_b_id": {
"title": "Entity B Id",
"type": "string"
},
"api_key": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Api Key"
}
},
"required": [
"ranking_id",
"entity_a_id",
"entity_b_id"
],
"title": "icomply_explainArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "icomply_explainOutput"
}🟢aimrank_healthcheck
iCOMPLY contract: liveness + DB-connectivity probe.
输入模式
{
"type": "object",
"properties": {},
"title": "icomply_healthcheckArguments"
}输出模式
{
"type": "object",
"properties": {
"result": {
"additionalProperties": true,
"title": "Result",
"type": "object"
}
},
"required": [
"result"
],
"title": "icomply_healthcheckOutput"
}社区
证据