mcp · handle iron_manus_mcp
Rube · job 76%doriku · job 75%taskflow_mcp · job 75%forkit · job 79%Athenic · job 76%agent_orchestration · job 79%mcp_task_orchestrator · job 76%retasc · job 77%task_orchestrator · job 79%objective · job 77%kanban_mcp · job 75%bitontree_ai_agent_development · job 71%model_context_shell · job 72%agentda · job 75%Swarm MCP Server · job 79%tasklix · job 72%skills_over_mcp · job 74%forge_think · job 73%Docket · job 75%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