mcp_github_mapper · job 77%CookieGli · job 80%RepoSage · job 79%agentmako · job 83%omen · job 77%Menhir · job 77%Euthynos · job 84%RepoContext · job 81%codenib · job 79%Feinman · job 88%LayerMap · job 87%Loctree · job 77%Corulix · job 85%Codebase Archaeology MCP · job 80%cairn · job 77%MAW-KG · job 79%Bridger · job 80%orbitkb · job 80%Ripple · job 80%mysid · job 80%LAIN · job 79%Jevex · job 79%corbel · job 84%CodeGraph MCP · job 79%Verinoda Symbiosis · job 78%whichlib · job 77%Codex Free Worker · job 76%painpoints · job 78%Cortex · job 82%Mezura · job 78%BlastCode · job 82%wryneck · job 79%Jev Agent Quality · job 79%MCP Tree-sitter Server · job 78%slimdex · job 86%Context Crafter MCP · job 80%Norma MCP Server · job 81%gitintel_mcp · job 76%roam_code · job 82%code-intel · job 91%Chronos-Agent · job 80%symvanta · job 82%sverklo · job 80%MIMRY · job 84%MindCtx · job 78%Ripplet · job 84%CodeDiver · job 83%Reliary · job 81%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