mcp · handle codexray
codex_mcp_tool · job 78%Pensieve · job 77%Pith · job 79%sumgrep · job 78%codebase_rag · job 74%Verinoda Symbiosis · job 78%graft-Max · job 85%trace-mcp · job 82%monomind · job 78%code_context_engine · job 81%knowledge_rag · job 73%minga-graph · job 77%chat-recall · job 78%thimiko · job 75%ragd MCP · job 75%stash · job 77%code_memory · job 82%MCP RAGdown · job 73%atlas_scout_mcp · job 73%ontomics · job 73%CodeMemory · job 76%Agent Chat Search · job 73%Vera · job 78%Codex Context MCP · job 75%Knowledge Base · job 82%Obsidian RAG MCP · job 77%DeepSeek Subagent MCP · job 75%Sonar · job 77%longhand · job 76%code_graph_mcp · job 76%Delphi Code · job 77%EtherPK · job 74%Codebase Copilot · job 84%zt-memory · job 75%sverklo · job 77%repobase · job 78%ProjectRecall · job 76%repo-graph-mcp · job 73%Reflex · job 76%Agent Memory Share MCP · job 79%ken-rank · job 79%brok · job 78%GraphRelay · job 79%mcp_deepcontext · job 75%code_graph_rag · job 80%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