mcp · handle mcai_knowledge
fortemi · job 82%documentize_mcp · job 80%Local Worker MCP · job 77%Signal · job 79%Keepygaga RAG · job 81%llmtomd · job 77%DocuGraph MCP · job 80%Knowledge Base Server · job 81%capture · job 81%DocSift · job 77%gemina · job 80%Frenchie · job 81%documentpro · job 77%mindola · job 80%Kephalaion · job 81%qdrant_loader · job 77%Trove · job 78%ilias_miraoui_pennyocr_mcp · job 78%EdgeEver · job 76%AgentFlow · job 78%RAG as MCP · job 83%Books MCP · job 76%sarvcrawl · job 84%3Q PDF · job 81%LanceDB Search MCP · job 79%Kimono MCP Server · job 79%KnowledgeRail · job 78%Knowledge Raven · job 76%mcp_docs_provider · job 76%Agentic-KB · job 79%agent_library · job 78%CliDeck MCP · job 78%songofhawk_doco · job 82%Consumer · job 84%MemoryVault · job 78%PaperBotAI · job 81%PDFLean MCP Server · 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