mcp · handle sub_agents_mcp_2
pi_delegate_mcp · job 77%throng-mcp · job 73%claude_octopus · job 77%Hive · job 79%Subagent MCP · job 78%patchloom · job 77%subtask · job 74%codegraff · job 79%qwen-cli-mcp · job 81%Codex-Compatible MCP · job 78%Local Agent Automation MCP · job 77%Atomic Reps · job 75%sub_agents_mcp · job 81%zcode-mcp · job 79%agentlab_deploy · job 75%hub · job 75%agent_orchestrator_2 · job 76%OpenCode MCP Orchestrator · job 77%Strata Coder · job 77%claude_code_mcp · job 77%toke_local · job 82%micropage · job 76%Codex CLI Sync MCP · job 74%sudocode · job 73%claude_bridge_mcp · job 77%dsh-mcp · job 76%Verinoda Symbiosis · job 76%codex_mcp_bridge · job 76%Serena · job 77%promptarch · job 77%Pi Session MCP · job 74%mcp_tasks · job 76%CC Code MCP · job 78%skill_mcp · job 75%gpt2agent · job 73%agent-hub · job 79%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