Pqs Prompt Quality Score

Name: Pqs Prompt Quality Score
Author: OnChainAIIntel

@OnChainAIIntel

关于 Pqs Prompt Quality Score

The world's first named AI prompt quality score. Score any LLM prompt before it hits any model — returns grade (A-F), score out of 40, percentile, and dimension breakdown across 8 quality dimensions.

#prompt-engineering #prompt-quality #llm-evaluation #scoring #optimization #x402 #evaluation #prompt-scoring #ai-quality #base

基本信息

分类

其他

许可证

MIT

运行时

node

传输方式

stdio

发布者

OnChainAIIntel

提交者

OnChainAIIntel

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "pqs": {
      "command": "npx",
      "args": [
        "pqs-mcp-server"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is PQS?

PQS (Prompt Quality Score) is an MCP server that scores and optimizes LLM prompts before they reach any AI model. It evaluates prompts across eight dimensions (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure) and returns a 0–80 score with an A–F grade. It is built on PEEM, RAGAS, MT-Bench, G-Eval, and ROUGE, and is intended for developers and teams who want to improve prompt quality and reduce wasted inference spend.

How to use PQS?

Install via npx -y pqs-mcp-server in your Claude Desktop config (stdio) or use the remote HTTP URL https://promptqualityscore.com/api/mcp for streamable-HTTP clients. Run npx pqs-mcp-server directly. The free score_prompt tool requires no API key; the optimize_prompt tool requires a Pro subscription ($19.99/mo). Use the quality gate pattern to reject prompts scoring below 56/80.

Key features of PQS

Scores prompts on 8 dimensions (clarity, specificity, etc.)
Returns a 0–80 score and A–F grade
Free score_prompt tool with per-IP rate limits
Pro optimize_prompt rewrites and compares prompts
Side-by-side before/after outputs from a frontier model
Can be used as a pre-inference quality gate
Supports self-hosting via PQS_BASE environment variable

Use cases of PQS

Automatically reject low-quality prompts before they reach an LLM
Diagnose weak dimensions (e.g., specificity, context) in existing prompts
Optimize prompts by rewriting them and comparing output quality
Enforce prompt quality standards in CI/CD pipelines
Reduce inference costs by filtering out prompts that will produce poor results

FAQ from PQS

What is the free `score_prompt` tool?

It returns a 0–80 score, A–F grade, an 8‑dimension breakdown, and the weakest dimension. No API key is required. It is rate‑limited per IP: 5/min, 10/day, 100/month.

How do I install the PQS MCP server?

Add the server to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json) using npx -y pqs-mcp-server. For remote clients, use the URL https://promptqualityscore.com/api/mcp. You can also add it via Smithery (smithery mcp add onchaintel/pqs).

What are the rate limits for the free tool?

Per IP: 5 calls per minute, 10 per day, 100 per month. If exceeded, the tool returns a structured rate_limit_exceeded payload with subscribe and account URLs.

How do I use the `optimize_prompt` tool?

It requires a Pro subscription ($19.99/mo, 1,000 calls/mo). It rewrites the prompt to score higher, runs both versions through a frontier model, and returns the optimized prompt, before/after dimension scores, improvement percentage, and side‑by‑side sample outputs.

Can I self‑host PQS?

Yes. Set the PQS_BASE environment variable to your own backend URL (e.g., https://your-pqs-host.example.com). The default is https://promptqualityscore.com.