mcp · handle knowledge_rag
mnemo_2 · job 71%longhand · job 75%zai_web_search_mcp · job 74%calibremcp · job 71%claude_mem_lite · job 72%memoryos · job 71%rtfm · job 74%omniclip_rag · job 71%houtini_mcp_tools · job 74%agent_library · job 75%synapse · job 77%thimiko · job 73%memex_mvp · job 72%research_oyster · job 73%claude_code_session_mcp · job 73%synorive · job 79%Claude KB · job 83%Local RAG MCP · job 75%MCP RAG Server · job 74%Agent Knowledge Memory Wiki · job 73%Askline · job 74%mcp-docs-ask · job 72%CC Code MCP · job 72%Sherpa MCP · job 74%Phonotheca 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