About Digital AI Testing MCP
Digital AI Testing MCP is an MCP server published by digitalai-opensource in the Developer Tools category: digital.ai Continuous Testing MCP Server.
The repository has 2 stars and 1 forks, with the last commit 3 days ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
From source
git clone https://github.com/digitalai-opensource/digital-ai-testing-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (4)
assess_comparison_confoundsVerdict — **clean / caveated / confounded** — by flagging any dimension other than the declared axis (device model, OS, OS version, network profile, project, transaction name) that varies across or within the sides, plus missing telemetry and sample imbalance.
Parameters not published.
compare_performance_transactionsTwo-set comparison; trimmed-mean/median/mean per side + delta and % change. MAD outliers excluded by default (≥4 samples/side). Pass `comparisonAxis` to embed a confound check.
Parameters not published.
detect_performance_outliersRobust median/MAD outlier flagging on a single set; returns the kept set and recommended exclusions/re-runs.
Parameters not published.
performance_transaction_controlPhase 2: generate fresh samples inside an inspection session — `start` (with an NV profile) → run the verified flow → `end` (names the record). Records appear in the reporter ~1 min later.
Parameters not published.
Ask AI
✦
Ask AI about Digital AI Testing MCP
Powered by Claude · Grounded in docs
I know everything about Digital AI Testing MCP. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.