The Aggregate — LLM benchmark aggregate MCP server
ai.theaggregate/the-aggregatetheaggregate.aistreamable-httpv1.0.2Scanned
LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.
8 tools: 1 change things and 7 only read.
- Reads private data · 1
- Reads text others write · 1
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the The Aggregate — LLM benchmark aggregate MCP server can do
The The Aggregate — LLM benchmark aggregate MCP server is published by theaggregate.ai, a domain the MCP Registry verified. It has 8 tools. It can create or change data (1 tool: about_the_aggregate), but cannot delete data. 7 tools only read.
1 tool reads private data (compare_models); 1 tool brings in text other people can write (get_benchmark).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 1.0.2.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Changes things 1Claude Code: ask
about_the_aggregateWhat this data is: the published rating method, current coverage counts, update cadence, and how to cite it.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it What this data is: the published rating method, current coverage counts, update cadence, and how to cite it.
Annotations the server declares
- title: About The Aggregate
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 7Show 7 read-only tools
compare_modelsHead-to-head between 2-4 models: aggregate ranks, rating gap with a significance note based on the standard errors, and notable benchmarks they share.Reads private dataNo findings
Why it is in this group
- The name "compare_models" says "compare": a word for reading.
What it can reach
- private-dataThe description's first sentence says "note": it reads notes.
Description, as the server wrote it 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.
Annotations the server declares
- title: Compare models
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_benchmarkOne 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.Reads text others writeNo findings
Why it is in this group
- The name "get_benchmark" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Benchmark detail
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_leaderboardTop of the cross-benchmark aggregate ranking: published Aggregate Ratings combine public benchmark evidence on one scale (call about_the_aggregate for the current coverage and meth…No findings
Why it is in this group
- The name "get_leaderboard" says "get": a word for reading.
Description, as the server wrote it Top of the cross-benchmark aggregate ranking: published Aggregate Ratings combine public benchmark evidence on one scale (call about_the_aggregate for the current coverage and method). One row per model by default, fused across reasoning-effort settings. Supports paging via limit/offset.
Annotations the server declares
- title: Aggregate leaderboard
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_modelOne 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)…No findings
Why it is in this group
- The name "get_model" says "get": a word for reading.
Description, as the server wrote it 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).
Annotations the server declares
- title: Model profile
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_prediction_duelGuesswork — 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 scor…No findings
Why it is in this group
- The name "get_prediction_duel" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Prediction duel standings
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_benchmarksFind benchmarks in the aggregate by (partial) name.No findings
Why it is in this group
- The name "search_benchmarks" says "search": a word for reading.
Description, as the server wrote it Find benchmarks in the aggregate by (partial) name. Returns model coverage, difficulty on the rating scale, and the benchmark page URL.
Annotations the server declares
- title: Search benchmarks
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_modelsFind ranked models by (partial) name or provider.No findings
Why it is in this group
- The name "search_models" says "search": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Search models
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:28 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://theaggregate.ai/mcp: tools/list returned 8 tools to an anonymous client, including about_the_aggregate (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools2 changed.~2 changedView diff
- Changed:about_the_aggregateChanges thingsdescription
- Changed:get_leaderboardOnly readsdescription
Install
Pinned to version 1.0.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http the-aggregate https://theaggregate.ai/mcpclaude mcp add --transport http the-aggregate https://theaggregate.ai/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__the-aggregate__get_leaderboard",
"mcp__the-aggregate__search_models",
"mcp__the-aggregate__get_model",
"mcp__the-aggregate__compare_models",
"mcp__the-aggregate__search_benchmarks",
"mcp__the-aggregate__get_benchmark",
"mcp__the-aggregate__get_prediction_duel"
],
"ask": [
"mcp__the-aggregate__about_the_aggregate"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as the-aggregate. Review it before you use it.
Capability tags behind 2 rules
- mcp__the-aggregate__compare_models private-data
- mcp__the-aggregate__get_benchmark untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.theaggregate/the-aggregate/verify?hash=d9bcd8a875407ef545082d6422cd04bfe37b3792e779f671982031d7203a9dce" | jq -e '.changed == false'Pinned hash d9bcd8a87540, from Nov 11, 2026, 22:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.theaggregate/the-aggregate/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.theaggregate/the-aggregate)Source: MCP Registry. Synced Oct 21, 2026, 17:43 UTC.
The Aggregate — LLM benchmark aggregate MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the The Aggregate — LLM benchmark aggregate MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the The Aggregate — LLM benchmark aggregate MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the The Aggregate — LLM benchmark aggregate MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the The Aggregate — LLM benchmark aggregate MCP server have?
- 8 tools: 1 write, 7 read. about_the_aggregate, get_leaderboard, search_models, get_model, compare_models, search_benchmarks, get_benchmark and get_prediction_duel.
Does the The Aggregate — LLM benchmark aggregate MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the The Aggregate — LLM benchmark aggregate MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the The Aggregate — LLM benchmark aggregate MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.