mcp · handle codeatlas
context_engine · job 80%repobase · job 77%synaptic · job 79%gortex · job 81%lybrary · job 80%opencode_history_mcp · job 76%code_memory · job 76%ctxo · job 77%KnowledgeRail · job 75%git_mimir · job 77%amdb · job 80%octocode · job 79%indxr · job 79%codebase_memory_mcp · job 83%leankg · job 82%AtlasBrain · job 87%Bridger · job 79%trace · job 78%orbitkb · job 78%aptu-coder · job 79%Glia · job 75%Cortex · job 81%dfine Semantic MCP · job 78%AnyIndex MCP · job 76%sqry · job 79%Wadah Engine · job 79%Reflex · job 80%Treeweft · job 76%Sourcelens · job 79%codebone · job 78%NervaPack · job 77%SyntaxRAG · job 81%CodeMap · job 81%DeltaContext · job 79%CodebaseRAG · job 75%ckb_code_knowledge_backend · job 78%trace_mcp · job 83%codemem · job 78%mcp_ragex · job 81%axon_mcp_server · job 81%codehelper · job 84%graph_memory · job 79%rtfm · job 83%qurio · job 79%graphmind · job 87%codemind · job 81%CICADA · job 82%roo_logger · job 75%code_context_engine · job 77%sense · job 80%pharaoh_so · job 75%gnosis_mcp · job 79%codeprism · job 75%symgraph · job 76%citegraph · 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