mcp · handle ministic_fishstick · source page
context_plus · job 74%forge_mcp · job 74%srag · job 82%code_memory · job 80%repo_semantic_search · job 78%pluck · job 75%code_context_engine · job 78%sourcerer_mcp · job 77%srclight · job 81%trace_mcp · job 78%lybrary_2 · job 80%repobase · job 83%ast_mcp_server · job 74%gnosis_mcp · job 83%ontomics · job 77%contextatlas · job 77%git_mimir · job 81%mcp_ragex · job 77%axon_mcp_server · job 79%rtfm · job 80%lybrary · job 82%octocode · job 79%semantic_code_mcp · job 79%sqry · job 77%Contour · job 77%MCP Codebase Server · job 77%Treeweft · job 81%CICADA · job 81%indexio · job 78%MCP Tree-sitter Server · job 80%speedread · job 79%Sourcelens · job 77%MCP Memories · job 74%Sourcerer MCP · job 86%siftr · job 77%RepoMind · job 77%Vera · job 78%LEANN .NET · job 77%SwiftVectorKit · job 79%Smart Coding MCP · job 77%Acemcp · job 79%Pith · job 78%FileSift · job 83%CodeMap · job 79%hep-index · job 77%RagPilot · job 81%Claude Context · job 78%AnyIndex MCP · job 83%Delphi Code · job 76%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