mcp · handle dazbench
nvm · job 77%projectbrain-mcp · job 80%FleetQ · job 78%Frenchie · job 79%agent_pm · job 77%web2mcp · job 79%pare · job 79%Todo4Agent · job 79%x402nano · job 82%ai_netcafe · job 80%employee_zero · job 79%TaskPile · job 76%Danube · job 82%Fast Agent · job 83%floot_mcp · job 81%vibekit_mcp · job 76%mcp_server_things · job 78%azure_devops_mcp_server · job 76%Giljo HQ · job 83%cracked · job 78%yashwantsandey2000_engram · job 80%Agent Relay · job 76%API Test MCP · job 78%sub_agents_mcp · job 78%workflow-mcp · job 82%mcp-forge · job 75%querypie_ai · job 78%humanforai · job 76%HumanPages.ai · job 77%Agents @Kopern.ai · job 81%mcp_server_node · job 76%mcp_tasks · job 76%mcp_task_orchestrator · job 81%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