# llmtest-mcp

> llmtest-mcp — tjacquesson-llmtest-mcp. Use this tool when you need to benchmark AI models on real-world prompts and find cost-effective alternatives. It solves problems of model selection and cost optimization by comparing performance across 340+ models, integrating with platforms like Claude Code, Cursor, and Windsurf. It takes in AI model inputs and outputs comparative performance and cost data, ideal for use cases where model efficiency and budget are key considerations.

Canonical page: https://skillsregistry.net/skills/tjacquesson-llmtest-mcp  
JSON: https://api.skillsregistry.net/v1/skills/tjacquesson-llmtest-mcp

## Description

MCP server for LLMTest — benchmark AI models on real prompts, find cheaper alternatives across 340+ models. Works with Claude Code, Cursor, Windsurf.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/tjacquesson/llmtest-mcp)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "tjacquesson-llmtest-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/tjacquesson-llmtest-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/tjacquesson-llmtest-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt