Cloud agents you can watch, on the AI you already pay for
MCP server for industrial software that lets AI assistants connect machines, build screens and analyze production data
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
TR
Pricing model
Freemium
Not given
Pricing
Free plan with 20 credits/month (about 4 hours of machine time). Starter at $30/mo with 400 credits/month (about 80 hours). Pro at $75/mo with 2,000 credits/month (about 400 hours). Max at $120/mo with 4,000 credits/month (about 800 hours). 1 credit equals 12 minutes on default Small devbox. Medium
Not given
Key features
Watch cloud agents in real-time with live terminal and file tree
Automated PR reviews with before/after screenshots
Video recording of agent actions
Scheduled automations daily or weekly
Live port previews for each port the agent opens
REST and WebSocket API for tasks and automations
Isolated Firecracker microVMs per task
Skills from repository SKILL.md files
Reply by email to pause and resume agent tasks
Connect machines and create devices from plain language instructions
Build process screens and report dashboards that engineers review before deployment
Define production assets and calculate OEE for discrete, continuous or batch processes
Query alarm statistics and production data in natural language
Support MCP protocol over network HTTP or local stdio connections
Works with any MCP-compatible AI client including desktop and self-hosted models
Role-based access control matching viewer, operator and administrator permissions
Audit logging of every write operation with user identification
Acknowledge alarms and record batch results within user permissions
Generate Python code examples for REST API integration
What makes it different
Open devboxes you can watch, not sealed boxes
Runs on your own AI provider account with no second bill
Pay only for compute, with no per-task fees or surprises
Code never used for training
Machines destroyed after use, never reused
Built-in MCP server in every product, no separate AI add-on or cloud service needed
Production data remains on-premise; nothing sent to cloud unless user's chosen AI model requires it
Drafts protect production: AI-created screens and dashboards reviewed before going live
Same access controls for AI as for people: roles, rights and logging
Assists in user's own language and explains PLCGateway features through built-in help
Aether
PLCGateway AI MCP