mcp · handle local_code_search
repobase · job 83%leankg · job 83%ops_codegraph_tool · job 81%codegraff · job 81%mimirs · job 85%roam_code · job 85%AnyIndex MCP · job 85%jcodemunch_mcp · job 81%sanjaya · job 84%CodeAtlas · job 78%code-rag-mcp · job 82%GraphRelay · job 83%indexio · job 79%opencode_history_mcp · job 82%trace_mcp · job 79%Gus · job 85%Open Context Engine · job 81%RagPilot · job 87%Pith · job 79%CodeCompass · job 85%CodePulse · job 79%Atrius Index · job 80%amdb · job 85%code_context_engine · job 82%pluck · job 81%code_memory · job 79%MIMRY · job 79%Sourcelens · job 81%zoekt_mcp · job 80%Reflex · job 82%srclight · job 85%Smart Coding MCP · job 80%SyntaxRAG · job 86%gnosis_mcp · job 81%SmartDrive-OS · job 86%Vera · job 89%sourcerer_mcp · job 82%xgrep · job 80%AtlasBrain · job 85%Sippion · job 86%lybrary · job 87%DeltaContext · job 82%FileSift · job 87%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