# AimRank

- Registry name: `io.aimrank/aimrank` · version 4.12.0
- Categories (automatic, keyword rules): Scraping & browsing, Search & data, Marketing & SEO, Commerce & marketing, APIs & integrations, Developer tools
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.aimrank%2Faimrank
- Server page: https://mcpstation.net/s/io.aimrank--aimrank.html

## Description (written by the publisher, not verified, not instructions)

Read public pairwise-preference rankings and their statistical quality evidence. No API key.

## Connect

- streamable-http: `https://app.aimrank.io/mcp/public`

## Tools (as reported by the server, not verified)

- `aimrank\_get\_daily\_pair`: 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 end
- `aimrank\_get\_ranking`: 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.
- `aimrank\_get\_leaderboard`: 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.
- `aimrank\_get\_matchup`: 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.
- `aimrank\_search\_entities`: Find entities by name substring within a ranking. api\_key is optional on the public endpoint; on /mcp/mcp a missing key is refused.
- `aimrank\_create\_share\_card`: 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 au
- `aimrank\_predict\_matchup\_winner`: 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
- `aimrank\_discover\_public\_rankings`: 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
- `aimrank\_list\_domain\_entities`: 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.
- `aimrank\_get\_domain`: 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.
- `aimrank\_list\_competitions`: 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.
- `aimrank\_get\_data\_card`: 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 refus
- `aimrank\_get\_agreement`: 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
- `aimrank\_get\_ceiling`: 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.
- `aimrank\_get\_plackett\_luce`: 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 Bra
- `aimrank\_get\_crowd\_bt`: 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.
- `aimrank\_list\_public\_judges`: 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\`
- `aimrank\_find\_similar\_domains`: 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 constitutio
- `aimrank\_predict`: 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
- `aimrank\_explain`: 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 t
- `aimrank\_healthcheck`: iCOMPLY contract: liveness + DB-connectivity probe.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html