mcp · handle context_engine_2
agentmako · job 80%code_context_engine · job 78%codescout · job 81%jcodemunch_mcp · job 73%context_engineering · job 73%codegraff · job 81%Euthynos · job 75%clangaroo · job 78%gortex · job 76%code-intel · job 76%lybrary · job 81%codesearch · job 72%atlas_scout_mcp · job 76%leankg · job 75%mimirs · job 80%codebaseagent_mcp · job 74%narsil_mcp · job 82%code_memory · job 78%Needle · job 73%roam_code · job 79%ops_codegraph_tool · job 76%pluck · job 74%qartez · job 73%relace_mcp · job 71%repobase · job 74%reporelay · job 72%slimdex · job 80%sanjaya · job 75%sense · job 79%agent_lsp · job 76%srclight · job 77%srag · job 73%sverklo · job 81%tree_sitter_analyzer · job 72%vscode_mcp · job 82%Repo Context MCP · job 78%speclaw · job 76%amdb · job 82%codebase_rag · job 72%Rune · job 79%Context Crafter MCP · job 75%trace-mcp · job 76%ken-rank · job 75%Koragraph · job 74%pi-mcp · job 77%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