The Aggregate — LLM benchmark aggregate
ai.theaggregate/the-aggregate
Fused LLM rankings: one IRT/Elo scale across ~5,000 public benchmark leaderboards, updated daily.
Description as published in the official MCP registry.
Answers the MCP handshake and lists its tools. Checked 2026-10-04.
What we measured
| Endpoint | https://theaggregate.ai/mcp | registry |
|---|---|---|
| Handshake | Answers the MCP handshake and lists its tools (777 ms) | our check, 2026-10-04 |
| Protocol version | 2025-06-18 | our check, 2026-10-04 |
| Tools (8) | get_leaderboard, search_models, get_model, compare_models, search_benchmarks, get_benchmark, get_prediction_duel, about_the_aggregate | tools/list, 2026-10-04 |
| Registry version | 1.0.1 · active · updated 2026-07-25 | registry |
Signed reports
No signed reports yet. A report carries a signed decision record from the reporter's gate, so it shows a real call went through, not just an opinion. How to file one.
Connect
claude mcp add --transport http the-aggregate https://theaggregate.ai/mcpCommands are built from the registry entry. Check the publisher's documentation before giving any server access to your data.
Related servers
- SigRank — AI Operator Benchmarking SigRank benchmark MCP: cascade metrics, leaderboard, operator profiles, simulation…
- CounterScript - Drug Price Benchmarks Free US drug-price benchmarks from federal data (CMS NADAC): a benchmark, not a price…
- Dataset Aggregate & Pivot GROUP BY and pivot tables for JSON rows: 11 functions, date buckets, top N, totals, messy…
- Dataset Aggregate, Group By & Pivot Returns GROUP BY and pivot tables for any Apify dataset, file or Google Sheet by URL, or…
- SQL Benchmarks Lab Query pre-computed SQL engine benchmarks. Runs standalone, no server setup required.
- mcp-benchmark-hygiene Detect pytest config-leakage that corrupts agent-benchmark grading. Deterministic, no-LLM.
Agents can read this page as data: MCP endpoint https://openforallofus.com/api/mcp, tool get_tool with name ai.theaggregate/the-aggregate.