Model Tested MCP Server

Install Model Tested MCP server

claude mcp add --transport http worker-jelly-ham https://modeltested.com/mcp

{
  "mcpServers": {
    "worker-jelly-ham": {
      "url": "https://modeltested.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "worker-jelly-ham": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://modeltested.com/mcp"
      ]
    }
  }
}

{
  "servers": {
    "worker-jelly-ham": {
      "type": "http",
      "url": "https://modeltested.com/mcp"
    }
  }
}

{
  "mcpServers": {
    "worker-jelly-ham": {
      "serverUrl": "https://modeltested.com/mcp"
    }
  }
}

Context tax

Connecting this server adds ~942 tokens of tool definitions to every model turn (lean, 5 tools). Measured 2026-10-19 via its hosted endpoint; o200k tokenizer, worst case for clients that load all tools up front. How we measure

Input prices as of 2026-10-06. Excludes your own prompt and output.

Tools (5)

• find_models258 tok

  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'.

• decision_models159 tok

  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.

• get_model147 tok

  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_articles108 tok

  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.

• compare_models97 tok

  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.

Security signals

92/100 — no known issues found as of 2026-10-19, from the checks below. This is not a guarantee of safety; review what a server can do before connecting it.

Scan it yourself before installing with vectra-guard, the open-source agent security CLI. Scoring rules

Freshness

Active — last maintenance signal today. The newest of the signals below sets the band.

1. Last commit (default branch)

   2026-10-18 · today · GitHub

2. Latest release

   no data · GitHub

3. Package published

   no data · npm/PyPI

4. Registry entry updated

   2026-10-18 · 1d ago · official registry · v1.0.0