mcp · handle sub_agents_mcp
toolhive · job 76%mistral_mcp · job 78%kagi_session2api_mcp · job 77%drawer | publish ai artifacts · job 72%mcp_tasks · job 76%langdock_agent_mcp_server · job 77%nocal_mcp · job 77%obsidian_llm_wiki · job 77%agent_library · job 79%mcpd · job 80%claude_ipc_mcp · job 74%blender_open_mcp · job 72%macos_mcp · job 76%TaskPile · job 73%openclaw_direct_openclaw · job 71%mcp_perplexity_server · job 72%syncpen · job 70%llmtomd · job 74%NEXUSRUN · job 75%promptarch · job 81%zen_mcp_2 · job 76%applescript_mcp · job 74%wcgw · job 74%hub · job 75%joplin_mcp · job 74%Dora · job 71%coding-agents-mcp · job 79%markitdown_mcp_server · job 75%AI Workbench MCP · job 75%dazbench · job 78%CC Code MCP · job 75%Agile Squad MCP · job 79%faraztools-mcp · job 77%MemorySync Cursor Starter · job 79%Brainy · job 77%aceto · job 73%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