# Theaggregate The Aggregate MCP server

Source: https://glimind.com/server/mcp-registry%2Fai.theaggregate%2Fthe-aggregate
Registry id: `mcp-registry/ai.theaggregate/the-aggregate`
Status: live (checked 2026-11-22T12:12:57.441Z)

## Verdict

Theaggregate The Aggregate MCP server answered 100% of Glimind's liveness checks over 30 days, better than 43% of MCP servers, with 315 ms median handshake and 0 outages in 90 days. Its agent-readiness grade is A (96/100) across 8 tools, costing an agent about 1,002 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 100% | 43% of MCP servers |
| Median handshake latency | 315 ms | 39% of MCP servers |
| p95 handshake latency | 713 ms | — |
| Checks in 30 days | 6,955 | — |
| Outages, 90 days | 0 | — |
| Median recovery | — | — |
| Agent-readiness score | 96/100 (A) | 74% of MCP servers |
| Tools | 8 | — |
| Tool-list size for an agent | ~1,002 tokens | 68% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "theaggregate-the-aggregate-mcp-server": {
      "type": "http",
      "url": "https://theaggregate.ai/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http theaggregate-the-aggregate-mcp-server https://theaggregate.ai/mcp
```

## Tools (8)

- `about_the_aggregate`: What this data is: the published rating method, current coverage counts, update cadence, and how to cite it.
- `compare_models`: Head-to-head between 2-4 models: aggregate ranks, rating gap with a significance note based on the standard errors, and notable benchmarks they share.
- `get_benchmark`: One benchmark in depth: what it measures, the original source leaderboard URL, IRT stats (difficulty, noise, model coverage), skill weights, and the current top
- `get_leaderboard`: Top of the cross-benchmark aggregate ranking: published Aggregate Ratings combine public benchmark evidence on one scale (call about_the_aggregate for the curre
- `get_model`: One model in depth: aggregate rank, Aggregate Rating with standard error, provider, what it is, cost per task where known, and its most notable benchmark result
- `get_prediction_duel`: 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
- `search_benchmarks`: Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the rating scale, and the benchmark page URL.
- `search_models`: Find ranked models by (partial) name or provider. Returns rank, Aggregate Rating and the model page URL. One row per model by default, fused across reasoning-ef

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
