# 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.

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add onchaintel/pqs

# Browse available tools
npx -y @smithery/cli@latest tool list onchaintel/pqs

# Get full schema for a tool
npx -y @smithery/cli@latest tool get onchaintel/pqs score_prompt

# Call a tool
npx -y @smithery/cli@latest tool call onchaintel/pqs score_prompt '{}'
```

## Direct MCP Connection

Endpoint: `https://pqs--onchaintel.run.tools`

**Optional config:**
- `api_key` (query) — PQS API key for paid endpoints (optimize, compare). Get one free at pqs.onchainintel.net

## Tools (3)

- `score_prompt` — Score any LLM prompt for quality using PQS. Returns a grade (A-F), score out of 40, and percentile. Free — no payment r…
- `optimize_prompt` — Score AND optimize any LLM prompt using PQS. Returns score, optimized prompt, and 8-dimension breakdown based on PEEM, …
- `compare_models` — Compare Claude vs GPT-4o on the same prompt. Scored head-to-head by a third model judge. Returns winner, scores, and re…

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get onchaintel/pqs <tool-name>
```