ken · job 73%kept · job 73%Marrine RAG MCP Server · job 76%Nibble · job 75%Catalog · job 74%SharePoint Search MCP · job 72%RAG Search MCP Server · job 72%MCP RAGdown · job 72%mnemodoc_server · job 77%neuroncite · job 77%OpenCode Document RAG MCP · job 72%Corpus · job 71%cowork_semantic_search · job 80%Hybrid RAG MCP · job 71%MCP RAG Server · job 77%knowledge_rag · job 75%SVDB MCP · job 75%MCPHybridRAG Server · job 77%Vexicon · job 75%aichallenge-rag · job 71%Scry MCP Server · job 74%LocalGate · job 76%dfine Semantic MCP · job 72%Agentic-RAG-MCP · job 74%MCP Documentation · job 76%Semlith · job 74%Pensieve · job 77%Privacy First Search Lab · job 74%RAG-MCP · job 74%semdex · job 76%AI Memory MCP · job 72%engram_engram_memory · job 72%Local Docs Copilot · job 78%rag-starter · job 74%Bismut Vector MCP · job 72%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