MCP ServerScored via MCP protocol probing: initialize handshake, tools/list conformance, and ping + tool invocation performance.
io.github.OnChainAIIntel/pqs-mcp-server
Score prompt quality across 8 dimensions before they reach a model. Pre-flight, not post-hoc.
90/100
Operational Score
Score Breakdown
Availability30/30
Conformance30/30
Performance30/40
Key Metrics
Uptime 30d
100.0%
P95 Latency
81.9ms
Conformance
Pass
Trend
Stable
What's Being Tested
Availability
HTTP health check to the service endpoint
Responded with HTTP 200 in 81ms
Conformance
MCP initialize handshake + tools/list
Valid MCP server info returned, tools/list responded
Performance
MCP ping + zero-arg tool invocation benchmarking
P95 latency: 81ms, task completion: 100%
Skills
score_prompt
Score any LLM prompt for quality using PQS. Returns a grade (A-F), score out of 40, and percentile. Free — no payment required. Use before sending any prompt to an LLM.
optimize_prompt
Score AND optimize any LLM prompt using PQS. Returns score, optimized prompt, and 8-dimension breakdown based on PEEM, RAGAS, G-Eval, MT-Bench. Costs $0.025 USDC via x402.
compare_models
Compare Claude vs GPT-4o on the same prompt. Scored head-to-head by a third model judge. Returns winner, scores, and recommendation. Costs $0.50 USDC via x402.
Tools
3 tools verified via live probeServer: pqs-mcp-serverVersion: 1.0.0Protocol: 2024-11-05
Recent Probe Results
| Timestamp | Status | Latency | Conformance |
|---|---|---|---|
| May 3, 2026 | success | 81.9ms | Pass |
Source Registries
mcp-registry
First Seen
Apr 29, 2026
Last Seen
May 2, 2026
Last Probed
May 3, 2026