cowork_semantic_search · job 77%graph_memory · job 73%costwise_mcp · job 76%codebase_rag · job 73%code_memory · job 78%codescout · job 74%srag · job 80%mcp_memento · job 76%arbor · job 72%repobase · job 79%codetree · job 81%gnosis_mcp · job 74%context_sherpa · job 73%mimirs · job 75%ken · job 78%ast_mcp_server · job 72%sense · job 84%contextatlas · job 73%context_engine · job 74%git_mimir · job 72%mcp_ragex · job 74%csharp_code_map · job 73%remembrallmcp · job 76%ctxo · job 77%context_plus · job 76%repo_semantic_search · job 73%lybrary · job 82%codesearch · job 85%lybrary_2 · job 78%codemind · job 82%gortex · job 83%leankg · job 75%codegraff · job 80%code_context_engine · job 79%Astra · job 74%srclight · job 79%sourcerer_mcp · job 80%Repo Context MCP · job 75%jcodemunch_mcp · job 79%ops_codegraph_tool · job 76%amdb · job 78%semantic_code_mcp · job 76%Context Engine · job 74%Ministic Fishstick · job 75%minh_gkg · job 75%CodeAtlas · job 73%sanjaya · job 74%narsil_mcp · job 77%KnowledgeRail · job 73%CookieGli · job 74%contextflux · job 74%indxr · job 72%ctx_5 · job 79%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