Model Tested MCP server
com.modeltested/llm-benchmarksmodeltested.comstreamable-httpv1.0.0Scanned
Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.
5 tools: 1 change things and 4 only read.
- Reads private data · 1
- Reads text others write · 0
- 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 Model Tested MCP server can do
The Model Tested MCP server is published by modeltested.com, a domain the MCP Registry verified. It has 5 tools. It can create or change data (1 tool: decision_models), but cannot delete data. 4 tools only read.
1 tool reads private data (find_models).
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.
Last scanned Nov 10, 2026, version 1.0.0.
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.
5 tools
Changes things 1Claude Code: ask
decision_modelsUse this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls.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 Use this whenever the user asks about decision models or LLMs for classification, routing, triage or yes/no calls. Accuracy on our decision test (routing tickets, applying rules, spotting phishing, flagging risky code changes), how well each model's confidence matches its accuracy (calibration), and API cost per 1,000 calls. Covers dedicated decision models and regular LLMs given the same tasks.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
Only reads 4Show 4 read-only tools
compare_modelsUse this whenever the user asks how two or more open-weight models compare, or which of them to pick.No findings
Why it is in this group
- The name "compare_models" says "compare": a word for reading.
Description, as the server wrote it Use this whenever the user asks how two or more open-weight models compare, or which of them to pick. Returns our test scores, rank and memory needs for 2 to 6 models side by side.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
find_modelsUse this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their graphics card (VRAM) or …Reads private dataNo findings
Why it is in this group
- The name "find_models" says "find": a word for reading.
What it can reach
- private-dataThe description's first sentence says "document": it reads documents.
Description, as the server wrote it Use this whenever the user asks which local or open-weight LLM is best, overall or for coding, documents or decisions, or which model they can run on their graphics card (VRAM) or Mac. Returns tested models ranked by our own test scores, best first; with a GPU or Mac memory size it only returns models that fit, plus the quantization to download and the memory it needs. Examples: 'best model for a 16 GB GPU', 'best coding model on a 32 GB Mac', 'best small model under 10B'.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
get_modelUse this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it needs, or which quant…No findings
Why it is in this group
- The name "get_model" says "get": a word for reading.
Description, as the server wrote it Use this whenever the user asks about a specific open-weight model: how good it is, its benchmark scores, whether it's worth using, how much VRAM or memory it needs, or which quantization to download. Returns our test scores, rank, memory at each quantization, the smallest GPU and Mac it fits, decision accuracy and our Q4 run on a Mac when there is one. Accepts a name or slug, e.g. 'qwen3.5 9b' or 'gpt-oss-20b'.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
search_articlesFind Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory.No findings
Why it is in this group
- The name "search_articles" says "search": a word for reading.
Description, as the server wrote it Find Model Tested articles and ranking pages by keyword, newest first: news about newly tested models, guides on quantization, Ollama and memory. Returns title, summary, date and link.
Annotations the server declares
- readOnlyHint: 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 untrusted-input or outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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, 18:42 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://modeltested.com/mcp: tools/list returned 5 tools to an anonymous client, including decision_models (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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http llm-benchmarks https://modeltested.com/mcpclaude mcp add --transport http llm-benchmarks https://modeltested.com/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__llm-benchmarks__find_models",
"mcp__llm-benchmarks__get_model",
"mcp__llm-benchmarks__compare_models",
"mcp__llm-benchmarks__search_articles"
],
"ask": [
"mcp__llm-benchmarks__decision_models"
],
"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 llm-benchmarks. Review it before you use it.
Capability tags behind 1 rule
- mcp__llm-benchmarks__find_models private-data
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/com.modeltested/llm-benchmarks/verify?hash=0e77251589554a0eada26b9135cc1195441f06720ea14305ddd0214039ba6739" | jq -e '.changed == false'Pinned hash 0e7725158955, from Nov 10, 2026, 21:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.modeltested/llm-benchmarks/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.modeltested/llm-benchmarks)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:59 UTC.
Model Tested MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Model Tested MCP server safe?
- No scan can promise that. What its definitions show: 5 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 Model Tested MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Model Tested 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 Model Tested MCP server have?
- 5 tools: 1 write, 4 read. decision_models, find_models, get_model, compare_models and search_articles.
Does the Model Tested MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Model Tested MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Model Tested MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.