# The Aggregate — LLM benchmark aggregate (remote · theaggregate.ai)

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

- Trust score: 66/100 (medium)
- Change this week: +1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `theaggregate.ai`: 66/100 (this document), [markdown](https://verifymcp.io/servers/ai-theaggregate-the-aggregate/theaggregate.md), [page](https://verifymcp.io/servers/ai-theaggregate-the-aggregate/theaggregate)

## Channel facts

- Endpoint: `https://theaggregate.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 60/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 8 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 615 tokens (~76/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

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

### Codex

```toml
[mcp_servers.ai-theaggregate-the-aggregate]
url = "https://theaggregate.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-theaggregate-the-aggregate": {
      "type": "remote",
      "url": "https://theaggregate.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-theaggregate-the-aggregate --url https://theaggregate.ai/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-theaggregate-the-aggregate:
    url: "https://theaggregate.ai/mcp"
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 65, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 65, −1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 65, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 64)

First indexed and scored.

## MCP tools (8)

### `get_leaderboard` (~84 tokens)

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.

Input parameters:

- `limit` (number): Rows to return (1-100, default 25).
- `offset` (number): Rows to skip from the top (default 0).

### `search_models` (~69 tokens)

Search models

Find ranked models by (partial) name or provider. Returns rank, Elo and the model page URL.

Input parameters:

- `limit` (number): Max results (1-25, default 10).
- `query` (string, required): Model or provider name fragment, e.g. "opus" or "deepseek".

### `get_model` (~76 tokens)

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).

Input parameters:

- `model` (string, required): Model name or slug, e.g. "Claude Opus 4.5" or "gpt-5-5".

### `compare_models` (~54 tokens)

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.

Input parameters:

- `models` (array, required): Two to four model names or slugs.

### `search_benchmarks` (~77 tokens)

Search benchmarks

Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the Elo scale, and the benchmark page URL.

Input parameters:

- `limit` (number): Max results (1-25, default 10).
- `query` (string, required): Benchmark name fragment, e.g. "swe-bench" or "arena".

### `get_benchmark` (~88 tokens)

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.

Input parameters:

- `benchmark` (string, required): Benchmark name or slug, e.g. "Aider polyglot".
- `top` (number): How many top models to list (1-50, default 10).

### `get_prediction_duel` (~58 tokens)

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.

### `about_the_aggregate` (~35 tokens)

About The Aggregate

What this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-theaggregate-the-aggregate/theaggregate#diagnostics

## Score history

- 2026-08-03: 66
- 2026-08-02: 66
- 2026-08-01: 65
- 2026-07-31: 65
- 2026-07-30: 65
- 2026-07-29: 66
- 2026-07-28: 66
- 2026-07-27: 65
- 2026-07-26: 64

## Links

- Remote endpoint: https://theaggregate.ai/mcp
- Website: https://theaggregate.ai/mcp
- Changelog RSS feed: https://verifymcp.io/servers/ai-theaggregate-the-aggregate/theaggregate/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-theaggregate-the-aggregate/theaggregate/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-theaggregate-the-aggregate/theaggregate