PQS scores any prompt before the model runs. 8 dimensions. 5 frameworks. Pre-flight, not post-hoc.
Dev & Codev1.4.0streamable-httppromptqualityscore.com repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 1423ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2024-11-05, serverInfo pqs-mcp-server@1.4.0 |
| tooling | 35 / 35 | tools/list OK: 2 tools e.g. "score_prompt"; 2/2 described, 2/2 fully-typed schemas, median description 1235 chars |
| latency | 7 / 10 | initialize round-trip 1423ms |
| provenance | 15 / 15 | description present; repository linked; version 1.4.0; namespace io.github.OnChainAIIntel matches endpoint/repo |
Score 97/100 · latency 1423ms · 2 tools · auth: open
Claude Code:
claude mcp add --transport http pqs-mcp-server https://promptqualityscore.com/api/mcp
Generic MCP client config:
{ "mcpServers": { "pqs-mcp-server": { "type": "http", "url": "https://promptqualityscore.com/api/mcp" } } }
MCP Queen is a graded index, not a middleman — your agent connects directly to the server above. Check the grade and evidence first; that's the point.
Share this server: permalink https://mcpqueen.com/s/io.github.OnChainAIIntel/pqs-mcp-server · referral link https://mcpqueen.com/go/io.github.OnChainAIIntel/pqs-mcp-server (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.OnChainAIIntel/pqs-mcp-server)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-13 18:18 | A | 97 | 1423ms |