mcp · handle gpt_admin
incident_io_mcp · job 73%Fedora Agents · job 74%ChatterLab · job 77%mcp_filesystem · job 73%netamv-mcp · job 74%Ubuntu VM Control MCP Server · job 75%wslgate · job 73%HelpDesk-MCP · job 77%Stand Pulse · job 78%ServerOps MCP · job 75%Bolt Panel · job 77%CreateOS MCP · job 83%fabrixai · job 74%Homelab · job 75%Shellit · job 84%PromptSwing · job 77%Windows-MCP — Hardened Fork · job 74%netdata_mcp · job 77%aws_security_mcp · job 77%powershell_mcp · job 74%SSH MCP · job 75%MCP Server SSH · job 84%HostingFor.AI · job 77%infrastructure_mcp · job 77%Linux MCP Daemon · job 76%Astra-MCP · job 74%ryns-code-mcp · job 82%Terminal Server · job 85%SSH Ops MCP · job 80%OSIR Agent Platform · job 77%Athena · job 74%Homelab MCP · job 79%AiStackOps · job 77%HOPX MCP Server · job 73%SSH Remote Bridge · job 73%vServer Monitoring MCP Server · job 74%Remote Desktop MCP (DV) · job 73%Domain Lab · job 80%Longarm MCP · 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