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

Discovery Engine

Discovery Engine is not another AI data analyst that writes pandas or SQL for you. Discovery Engine finds complex patterns in your data - feature interactions, nonlinear thresholds, and meaningful subgroups - without requiring prior hypotheses about what matters. Each pattern is validated on hold-out data, corrected for multiple testing, and checked for novelty against academic literature with citations. This is a computational pipeline, not prompt engineering over data. You cannot replicate what it does by writing pandas code or asking an LLM to look at a CSV. It finds structure that hypothesis-driven analysis misses, because it doesn't start with hypotheses.

47/100
Operational Score
Score Breakdown
Availability27/30
Conformance10/30
Performance10/40
Key Metrics
Uptime 30d
99.3%
P95 Latency
288.7ms
Conformance
Fail
Trend
Stable
What's Being Tested
Availability
HTTP health check to the service endpoint
Responded with HTTP 401 in 177ms
ConformanceNot tested
MCP initialize handshake + tools/list
Performance
MCP ping + zero-arg tool invocation benchmarking
P95 latency: 288ms, task completion: 0%
Recent Probe Results
TimestampStatusLatencyConformance
Apr 2, 2026success177.7msPass
Apr 2, 2026success172.9msPass
Apr 2, 2026success189.1msPass
Apr 2, 2026success178.7msPass
Apr 2, 2026success165.7msPass
Apr 2, 2026success178.4msPass
Apr 2, 2026success150.8msPass
Apr 2, 2026success197.7msPass
Apr 2, 2026success282msPass
Apr 2, 2026success176.5msPass
Source Registries
smithery
First Seen
Mar 26, 2026
Last Seen
Apr 1, 2026
Last Probed
Apr 2, 2026