io.github.OnChainAIIntel/pqs-mcp-server

skills: {'id': 'score_prompt', 'name': 'score_prompt', 'description': 'Score a prompt\'s quality across 8 dimensions BEFORE sending it to an expensive\nmodel. Returns a 0-80 score, an A-F grade, the per-dimension breakdown\n(clarity, specificity, context, constraints, output_format, role_definition,\nexamples, cot_structure), and the weakest dimension.\n\nUSE WHEN:\n- The user is workshopping a prompt and asks "is this good?" / "will this\n work?" / "should I add more detail?"\n- The user is about to send a long or expensive prompt to GPT-4, Claude Opus,\n or any frontier model, especially in a batch or automation context where\n rework is costly.\n- The user mentions iterating on a prompt that produced poor output and wants\n to diagnose what\'s missing.\n- The user pastes a prompt and asks for feedback on it.\n\nDO NOT USE WHEN:\n- The user is asking you to write a prompt for them (write it yourself first,\n then optionally call score_prompt to verify).\n- The prompt is conversational chat (this scores task-shaped prompts).\n\nCOST: Free, no API key required. Rate-limited per IP: 5/min, 10/day, 100/month.\nIf the user exceeds the limit, the response will include a structured upgrade\npath with subscribe and account URLs.\n\nLATENCY: ~2 seconds.', 'tags': [], 'examples': None, 'input_modes': None, 'output_modes': None}, {'id': 'optimize_prompt', 'name': 'optimize_prompt', 'description': 'Rewrite a prompt to score higher on the PQS rubric, AND show before/after\noutput comparisons so the user can see the impact. Returns the optimized\nprompt, the original PQS score, the optimized PQS score, and side-by-side\nsample outputs from a frontier model using both versions.\n\nUSE WHEN:\n- The user got a low score from score_prompt and asks how to improve.\n- The user explicitly asks to "improve" / "rewrite" / "fix" / "optimize" a\n prompt they pasted.\n- The user is dissatisfied with output quality from a previous prompt and\n asks how to get better results.\n- score_prompt returned a suggestion to invoke this tool.\n\nDO NOT USE WHEN:\n- The user just asked for a score (use score_prompt only — don\'t double up).\n- The user wants you to write a new prompt from scratch (write it directly).\n\nREQUIRES: A PQS API key from a Pro subscription ($19.99/month, 1,000 calls/mo,\nincludes batch + A/B comparison). If the user has not provided one, the tool\nreturns a clear subscription URL — pass that response to the user verbatim.\nDo not invent or guess API keys. There is no free trial of this tool; the\nuser must subscribe before the first call.\n\nCOST: Counted against your Pro subscription\'s monthly call quota.\n\nLATENCY: ~6-8 seconds.', 'tags': [], 'examples': None, 'input_modes': None, 'output_modes': None}; uptime_30d 1.0%; p95 175.4ms; conformance: pass

How to connect

https://promptqualityscore.com/api/mcp

curl -X POST https://promptqualityscore.com/api/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'