mcp · handle pi_session_mcp
agentbus · job 80%SynAgent MCP · job 73%Sol–Luna Orchestrator · job 74%DSH Subagent MCP · job 74%Codex CodeBuddy MCP · job 75%Memorix · job 79%Codex App MCP · job 81%Flyto2 Runtime · job 77%agent_orchestrator_2 · job 74%pi-delegate-mcp · job 77%Strata Coder · job 78%claude_code_mcp · job 81%Subagent MCP · job 83%Sub-Agents MCP Server · job 77%sub-pi-agent · job 78%TaskBridge · job 78%consult · job 74%claude_bridge_mcp · job 78%dsh-mcp · job 81%Codex Local Ops · job 77%ChatGPT Codex CLI Bridge · job 75%qwen-cli-mcp · job 78%rexec · job 76%Local Agent Automation MCP · job 77%zcode-mcp · job 82%Harness Starter · job 75%Navish Commander · job 79%Claude OpenCode MCP · job 76%agent-hub · job 80%buyong-mcp · job 82%pilink · job 80%pi_delegate_mcp · job 84%Hermes MCP Bridge · job 73%throng-mcp · job 75%tmux-agents · job 75%WorkBuddy Subagent Bridge · job 73%dsh-zcode-bridge · job 74%Local Agents MCP · job 75%Outsrc · job 78%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