mcp · handle sub_agents_mcp_3
tmux-agents · job 82%Basemind · job 77%codex_control_plane_mcp · job 76%Outsrc · job 82%morph · job 76%TaskBridge · job 79%Agents Bridge MCP · job 78%magents · job 78%frontier_orchestrator · job 77%agent-hub · job 82%PAL MCP Server · job 81%zcode-mcp · job 82%agent_intern · job 81%codex_mcp_tool · job 78%Effort · job 81%Agent Cowork Memory · job 77%codex_mcp_bridge · job 81%Task Journal · job 79%DSH Subagent MCP · job 79%Claude Codex MCP · job 80%pi_delegate_mcp · job 77%Kagero · job 78%throng-mcp · job 77%subtask · job 82%hub · job 77%agent_orchestrator_2 · job 76%mcp-delegate · job 77%claude_code_mcp · job 85%agent_mesh · job 79%coding-agents-mcp · job 82%cc-as-subagent · job 76%sub_agents_mcp · job 81%Pi Session MCP · job 77%Harness Starter · job 77%consult · job 77%codex_specialized_subagents · job 76%Antigravity MCP Bridge · job 76%CLI Subagents · job 81%Sol–Luna Orchestrator · job 77%claude_octopus · job 80%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