Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

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

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

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

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

{
  "mcpServers": {
    "the-aggregate": {
      "type": "http",
      "url": "https://theaggregate.ai/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=the-aggregate&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vdGhlYWdncmVnYXRlLmFpL21jcCJ9"
}

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

{
  "mcpServers": {
    "the-aggregate": {
      "httpUrl": "https://theaggregate.ai/mcp"
    }
  }
}

extensions:
  "the-aggregate":
    enabled: true
    name: "the-aggregate"
    type: streamable_http
    uri: "https://theaggregate.ai/mcp"
    timeout: 300

Quality 86 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene100 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations8 of 8 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 1,049 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability75 · weight 15

warn
stability.changes13 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

8 tools, about 1,049 tokens to load them all · tool set 3ab671a12696 · tools last changed 2026-10-12 · checked 2026-10-20 12:13 UTC

Tool changes

2026-10-12search_benchmarkschangeddescription
before
Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the Elo scale, and the benchmark page URL.
after · 90% of words in common
Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the rating scale, and the benchmark page URL.
2026-10-12compare_modelschangeddescription
before
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.
after · 92% of words in common
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.
2026-10-12get_modelchangeddescription
before
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).
after · 93% of words in common
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 results (with percentiles).
2026-10-12search_modelschangeddescription
before
Find ranked models by (partial) name or provider. Returns rank, Elo and the model page URL. One row per model by default, fused across reasoning-effort settings.
after · 89% of words in common
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-effort settings.
2026-10-12get_leaderboardchangeddescription
before
Top of the cross-benchmark aggregate ranking: every model placed on one Elo scale by an IRT model fit over public benchmark leaderboards (call about_the_aggregate for the current coverage counts). One row per model by default, fused across reasoning-effort settings. Supports paging via limit/offset.
after · 95% of words in common
Top of the cross-benchmark aggregate ranking: every model placed on one rating scale by an IRT model fit over public benchmark leaderboards (call about_the_aggregate for the current coverage counts). One row per model by default, fused across reasoning-effort settings. Supports paging via limit/offset.
2026-10-10about_the_aggregatechangedannotations
2026-10-10get_prediction_duelchangedannotations
2026-10-10get_benchmarkchangedannotations
2026-10-10search_benchmarkschangedannotations
2026-10-10compare_modelschangedannotations

Showing the latest 10. Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 82 / 100

no-repository

provenance55

liveness99

freshness100

hygiene80

+dns-namespace +website +reachable +uptime-98% +updated-11d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://theaggregate.ai/mcp` streamable-http	none	yes	98%	297 ms	2025-06-18	2026-10-20

Tools (8)

`about_the_aggregate`read-only	What this data is: how the IRT fusion works, current coverage counts, update cadence, and how to cite it.
`compare_models`read-only	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`read-only	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.
`get_leaderboard`read-only	Top of the cross-benchmark aggregate ranking: every model placed on one rating scale by an IRT model fit over public benchmark leaderboards (call about_the_aggregate for the current coverage counts). One row per model by default, fused across reasoning-effort settings. Supports paging via limit/offset.
`get_model`read-only	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 results (with percentiles).
`get_prediction_duel`read-only	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.
`search_benchmarks`read-only	Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the rating scale, and the benchmark page URL.
`search_models`read-only	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-effort settings.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "ai.theaggregate/the-aggregate",
  "title": "The Aggregate — LLM benchmark aggregate",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://theaggregate.ai/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.2",
  "websiteUrl": "https://theaggregate.ai/mcp",
  "description": "LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily."
}