The world's first named AI prompt quality score. Score any LLM prompt before it
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.
active Production-safe Score 94/100 http no auth
At a glance
| Endpoint | https://promptqualityscore.com/api/mcp |
|---|---|
| Source | https://github.com/OnChainAIIntel/pqs-mcp-server |
| Transport | http |
| Tools | 2 |
| Auth | none |
| First seen | 2026-05-23 10:40:47 |
| Last checked | 2026-11-17 21:42:43 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 414 / 727 ms |
| Last successful check | 2026-11-17 21:42:43 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (2)
score_prompt— 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-dimensionoptimize_prompt— 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 opt
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:42:43 | ✓ | ✓ | 467 ms | 90 | active |
| 2026-11-17 21:27:43 | ✓ | ✓ | 510 ms | 90 | active |
| 2026-11-17 21:12:40 | ✓ | ✓ | 310 ms | 90 | active |
| 2026-11-17 20:55:59 | ✓ | ✓ | 445 ms | 90 | active |
| 2026-11-17 20:40:57 | ✓ | ✓ | 448 ms | 90 | active |
| 2026-11-17 20:25:56 | ✓ | ✓ | 472 ms | 90 | active |
| 2026-11-17 20:10:37 | ✓ | ✓ | 401 ms | 90 | active |
| 2026-11-17 19:54:54 | ✓ | ✓ | 436 ms | 90 | active |
| 2026-11-17 19:39:48 | ✓ | ✓ | 442 ms | 90 | active |
| 2026-11-17 19:24:31 | ✓ | ✓ | 318 ms | 90 | active |
| 2026-11-17 19:09:24 | ✓ | ✓ | 486 ms | 90 | active |
| 2026-11-17 18:54:16 | ✓ | ✓ | 293 ms | 94 | active |
| 2026-11-17 18:39:10 | ✓ | ✓ | 557 ms | 90 | active |
| 2026-11-17 18:24:03 | ✓ | ✓ | 297 ms | 94 | active |
| 2026-11-17 18:08:50 | ✓ | ✓ | 2031 ms | 87 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://promptqualityscore.com/api/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/promptqualityscore-com-api-mcp # JSON