mcp · handle session_export
codex_mcp_tool · job 75%roo_logger · job 71%Notion AI Hub · job 72%memex_mvp · job 70%ai_omni_skills · job 74%skill_search · job 71%rtfm · job 73%opencode_history_mcp · job 75%Waypoint · job 78%MCP OpenAI · job 76%aiAgentBridge · job 76%Claude Codex MCP · job 75%Obsidiyan Engine · job 78%Claude–Codex Session Link · job 75%CodeMemory · job 73%thimiko · job 70%mcp_opencode · job 73%session-hub · job 73%chat-recall · job 74%MCP Memories · job 73%Agents Bridge MCP · job 78%Tailpipe · 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