Pqs Prompt Quality Score

@OnChainAIIntel

About 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

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

Score a prompt's quality across 8 dimensions BEFORE sending it to an expensive model. Returns a 0-80 score, an A-F grade, the per-dimension breakdown (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure), and the weakest dimension. USE WHEN: - The user is workshopping a prompt and asks "is this good?" / "will this work?" / "should I add more detail?" - The user is about to send a long or expensive prompt to GPT-4, Claude Opus, or any frontier model, especially in a batch or automation context where rework is costly. - The user mentions iterating on a prompt that produced poor output and wants to diagnose what's missing. - The user pastes a prompt and asks for feedback on it. DO NOT USE WHEN: - The user is asking you to write a prompt for them (write it yourself first, then optionally call score_prompt to verify). - The prompt is conversational chat (this scores task-shaped prompts). COST: Free, no API key required. Rate-limited per IP: 5/min, 10/day, 100/month. If the user exceeds the limit, the response will include a structured upgrade path with subscribe and account URLs. LATENCY: ~2 seconds.

Rewrite a prompt to score higher on the PQS rubric, AND show before/after output comparisons so the user can see the impact. Returns the optimized prompt, the original PQS score, the optimized PQS score, and side-by-side sample outputs from a frontier model using both versions. USE WHEN: - The user got a low score from score_prompt and asks how to improve. - The user explicitly asks to "improve" / "rewrite" / "fix" / "optimize" a prompt they pasted. - The user is dissatisfied with output quality from a previous prompt and asks how to get better results. - score_prompt returned a suggestion to invoke this tool. DO NOT USE WHEN: - The user just asked for a score (use score_prompt only — don't double up). - The user wants you to write a new prompt from scratch (write it directly). REQUIRES: A PQS API key from a Pro subscription ($19.99/month, 1,000 calls/mo, includes batch + A/B comparison). If the user has not provided one, the tool returns a clear subscription URL — pass that response to the user verbatim. Do not invent or guess API keys. There is no free trial of this tool; the user must subscribe before the first call. COST: Counted against your Pro subscription's monthly call quota. LATENCY: ~6-8 seconds.

Overview

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.

Frequently asked questions

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?

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`.

Comments

Basic information

More Other MCP servers

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K