Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "llm-benchmarks": {
      "type": "http",
      "url": "https://modeltested.com/mcp"
    }
  }
}

claude mcp add --transport http llm-benchmarks https://modeltested.com/mcp

[mcp_servers.llm-benchmarks]
url = "https://modeltested.com/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "llm-benchmarks": {
      "type": "remote",
      "url": "https://modeltested.com/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "llm-benchmarks": {
      "type": "http",
      "url": "https://modeltested.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=llm-benchmarks&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbW9kZWx0ZXN0ZWQuY29tL21jcCJ9"
}

{
  "servers": {
    "llm-benchmarks": {
      "type": "http",
      "url": "https://modeltested.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "llm-benchmarks": {
      "httpUrl": "https://modeltested.com/mcp"
    }
  }
}

extensions:
  "llm-benchmarks":
    enabled: true
    name: "llm-benchmarks"
    type: streamable_http
    uri: "https://modeltested.com/mcp"
    timeout: 300

Quality 81 / 100new

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-11-25; 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 hygiene86 · 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.annotations5 of 5 tools declare readOnlyHint or destructiveHint
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: decision_models (destructiveHint, idempotentHint); search_articles (destructiveHint, idempotentHint); find_models (destructiveHint, idempotentHint); …
pass
tools.token_costabout 816 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stabilityn/a · weight 15

n/a
stability.changes, stability.rug_pulltool history recorded for 1 of the 7 days needed

dependenciesn/a · weight 15

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

5 tools, about 816 tokens to load them all · tool set aa91d06ed712 · checked 2026-10-19 10:52 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

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 96 / 100

provenance85

liveness100

freshness100

hygiene100

+repository +dns-namespace +website +reachable +uptime-100% +updated-1d-ago

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://modeltested.com/mcp` streamable-http	none	yes	100%	202 ms	2025-11-25	2026-10-19

Tools (5)

`compare_models`read-only	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.
`decision_models`read-only	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.
`find_models`read-only	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'.
`get_model`read-only	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'.
`search_articles`read-only	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.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "com.modeltested/llm-benchmarks",
  "title": "Model Tested",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://modeltested.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "repository": {
    "url": "https://github.com/jelly-ham/modeltested",
    "source": "github",
    "subfolder": "site/worker"
  },
  "websiteUrl": "https://modeltested.com/mcp/",
  "description": "Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons."
}