mcp · handle knowledge_rag
memoryos · job 71%calibremcp · job 71%rtfm · job 74%claude_mem_lite · job 72%mnemo_2 · job 71%longhand · job 75%houtini_mcp_tools · job 74%zai_web_search_mcp · job 74%agent_library · job 75%dfine Semantic MCP · job 73%Claude KB · job 83%Claude Context Hub · job 76%Free Search MCP · job 75%Verinoda Symbiosis · job 75%synapse · job 77%mcp-docs-ask · job 72%thimiko · job 73%memex_mvp · job 72%AsterMind MCP · job 75%Codebase Copilot · job 75%research_oyster · job 73%ProjectRecall · job 80%synorive · job 79%Edith Second Brain · job 73%trace-mcp · job 72%MCP RAG Server · job 74%CodeMemory · job 73%claude_code_session_mcp · job 73%Pensieve · job 82%Sherpa MCP · job 74%Knowledge Base · job 76%Local RAG MCP · job 75%Obsidian RAG MCP · job 81%Claude Brain · job 79%Agentic-RAG-MCP · job 76%Practitioner Knowledge MCP · job 73%ClaudeBase · job 76%Agent Review MCP · job 72%stash · job 81%MCP RAGdown · job 77%OCR MCP · job 75%Cription MCP Server · job 72%CommandCode MCP Server · job 71%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