mcp · handle sub_agents_mcp_4
mithril · job 82%Outsrc · job 76%Kagero · job 74%opencode-mcp · job 80%wcgw · job 78%TidyCode MCP · job 80%claude_code_mcp · job 77%PAL MCP Server · job 82%patchloom · job 78%pi-mcp · job 77%tmux-agents · job 77%ai_omni_skills · job 75%Sub-Agents MCP Server · job 88%Context Packer · job 75%taskdeck · job 77%kaban · job 75%ask-fable · job 74%consult · job 74%sub_agents_mcp · job 80%Roundtable AI · job 75%rexec · job 79%runtool · job 77%HypAware Plugin · 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