mcp · handle code_rag_mcp
codebase_rag · job 78%pgr · job 77%Needle · job 75%SCS · job 85%mcp_memento · job 77%codesearch · job 86%sourcerer_mcp · job 76%sift · job 76%pluck · job 79%code_context_engine · job 81%wryneck · job 80%agentmako · job 79%Codebase Copilot · job 81%sanjaya · job 76%RepoMind · job 83%jcodemunch_mcp · job 77%Context Engine · job 80%codenib · job 78%srclight · job 84%contextflux · job 77%code-search · job 78%Acemcp · job 78%srag · job 78%Sippion · job 78%Contour · job 77%Delphi Code · job 83%AnyIndex MCP · job 79%MIMRY · job 85%skimsearch · job 82%SyntaxRAG · job 82%cairn · job 78%Vera · job 81%Basemind · job 80%CodeDiver · job 79%indexio · job 76%LEANN .NET · job 79%semantic_code_mcp · job 79%reporelay · job 78%gnosis_mcp · job 76%Cortex · job 83%codegraff · job 83%repobase · job 82%markdown-memory · job 76%DeltaContext · job 77%ken · job 81%slimdex · job 85%code_memory · job 80%repo_semantic_search · job 79%MindCtx · job 78%FileSift · job 82%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