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