mcp · handle auto_qa
Witness · job 79%Playwright E2E MCP · job 90%QAJev · job 77%Kernel · job 82%Proofhand · job 75%aioproductos_studio · job 75%qa-screens · job 77%browser-hands · job 82%Mimiq · job 76%Parallel Browser MCP · job 80%Fast Browser · job 75%Persqo MCP Server · job 74%Cucumber Playwright MCP · job 72%Vouch · job 72%Frontend Stack MCP · job 73%Playwright AI Agent POM MCP Server · job 75%OpenProof · job 74%Cognitive Browser · job 74%AI Web Tester · job 79%Botcan · job 79%Playwright Trace Doctor · job 75%TestMu AI MCP Server · job 74%MCP-Server-Playwright · job 85%browser-memory · job 81%SceneScout · job 86%Agent Decision Kit · job 75%InfiAutomation MCP · job 76%OpenUI Engine · job 81%loadster · job 81%bugagent_mcp · job 84%qualitymax_mcp · job 73%Currents · job 76%CodeCheck MCP · job 88%Lite Locator MCP · job 77%yatt-ts · job 81%TestLens · job 82%Argus QA MCP · job 92%blindqa · job 86%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series