mcp · handle delphi_code
ken-rank · job 74%semdex · job 77%mcp_memento · job 78%git_mimir · job 77%coco_search · job 73%codesearch · job 80%sourcerer_mcp · job 74%codebase_rag · job 79%pgr · job 72%nxm-memory · job 76%SCS · job 79%code-rag-mcp · job 83%code_memory · job 86%RAG Search MCP Server · job 74%MIMRY · job 80%lybrary · job 82%Semlith · job 77%indexio · job 77%code-search · job 81%mcp_local_rag_2 · job 76%Ministic Fishstick · job 76%repobase · job 85%Bismut Vector MCP · job 74%MCP Codebase Server · job 77%ontomics · job 77%jcodemunch_mcp · job 75%Astra · job 75%mimirs · job 79%semantic_code_mcp · job 82%RepoMind · job 85%Sonarless MCP · job 73%Vera · job 81%Codebase Copilot · job 75%code_context_engine · job 83%forge_mcp · job 74%srag · job 81%repo_semantic_search · job 81%Acemcp · job 80%opencode_history_mcp · job 75%FileSift · job 82%srclight · job 85%Contour · job 83%Context Engine · job 78%skimsearch · job 78%reporelay · job 75%AnyIndex MCP · job 81%LEANN .NET · job 75%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