mcp · handle claude_code_session_mcp
knowledge_rag · job 73%claude_usage · job 75%thimiko · job 78%melytics · job 74%Perfect Memory MCP · job 74%Suvadu · job 81%chat-recall · job 78%stash · job 76%cc-handoff · job 76%Code Therapy · job 77%claude-remote · job 77%nouez · job 76%Claude Context Hub · job 80%Claude KB · job 78%Codex History MCP Bridge · job 75%claude-dig · job 78%longhand · job 78%Notion AI Hub · job 71%flatten_mcp · job 71%RelayHistory · job 73%Memória · job 75%Contextburn · job 79%Daybook MCP · job 75%Phonotheca MCP Server · job 82%claudeusage · job 77%Claude Shared Memory · job 75%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