3 tools from the Pqs MCP Server, categorised by risk level.
View the Pqs policy →compare_models Compare how Claude vs GPT-4o handles the same prompt using PQS. Both models are scored head-to-head by a third model judge. Returns winner, scores,... optimize_prompt Score AND optimize any LLM prompt using PQS. Returns the original score, an optimized version of the prompt, and dimension-by-dimension breakdown a... score_prompt Score any LLM prompt for quality using PQS (Prompt Quality Score). Returns a grade (A-F), score out of 40, and percentile. Free tier — no payment r... The Pqs MCP server exposes 3 tools across 1 categories: Read.
Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Pqs server.
Pqs tools are categorised as Read (3). Each category has a recommended default policy.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.