# The Aggregate — LLM benchmark aggregate MCP server

Fused LLM rankings: one IRT/Elo scale across ~5,000 public benchmark leaderboards, updated daily.

## Links
- Registry page: https://www.getdrio.com/mcp/ai-theaggregate-the-aggregate
- Repository: https://github.com/Sandell0/llm-leaderboard
- Website: https://theaggregate.ai/mcp

## Install
- Endpoint: https://theaggregate.ai/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://theaggregate.ai/mcp

## Tools
- get_leaderboard (Aggregate leaderboard) - Top of the cross-benchmark aggregate ranking: every model placed on one Elo scale by an IRT model fit over ~5,000 public benchmark leaderboards. Supports paging via limit/offset. Endpoint: https://theaggregate.ai/mcp
- search_models (Search models) - Find ranked models by (partial) name or provider. Returns rank, Elo and the model page URL. Endpoint: https://theaggregate.ai/mcp
- get_model (Model profile) - 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). Endpoint: https://theaggregate.ai/mcp
- compare_models (Compare models) - 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. Endpoint: https://theaggregate.ai/mcp
- search_benchmarks (Search benchmarks) - Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the Elo scale, and the benchmark page URL. Endpoint: https://theaggregate.ai/mcp
- get_benchmark (Benchmark detail) - 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. Endpoint: https://theaggregate.ai/mcp
- get_prediction_duel (Prediction duel standings) - 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. Endpoint: https://theaggregate.ai/mcp
- about_the_aggregate (About The Aggregate) - What this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it. Endpoint: https://theaggregate.ai/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: ai.theaggregate
- Version: 1.0.1
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 25, 2026
- Source: https://registry.modelcontextprotocol.io