Leaderboard/promptscan
MCP ServerScored via MCP protocol probing: initialize handshake, tools/list conformance, and ping + tool invocation performance.

promptscan

Production-ready prompt injection detection for AI agents. Scan user input, retrieved docs, and tool outputs before passing them to an LLM. Returns injection_detected, score, attack_type, and sanitized text.

57/100
Operational Score
Score Breakdown
Availability30/30
Conformance10/30
Performance17/40
Key Metrics
Uptime 30d
100.0%
P95 Latency
238ms
Conformance
Fail
Trend
Stable
What's Being Tested
Availability
HTTP health check to the service endpoint
Responded with HTTP 401 in 187ms
ConformanceNot tested
MCP initialize handshake + tools/list
Performance
MCP ping + zero-arg tool invocation benchmarking
P95 latency: 238ms, task completion: 0%
Recent Probe Results
TimestampStatusLatencyConformance
Apr 14, 2026success187msPass
Apr 14, 2026success145.4msPass
Apr 14, 2026success238msPass
Apr 14, 2026success225.6msPass
Source Registries
smithery
First Seen
Apr 14, 2026
Last Seen
Apr 14, 2026
Last Probed
Apr 14, 2026
promptscan — Chiark Agent Quality Index