MCP server for industrial software that lets AI assistants connect machines, build screens and analyze production data
Serverless sandboxes that bill only for the seconds your agent's code runs
Stage
Not given
MVP
Founded
Not given
Not given
Based in
TR
MX
Pricing model
Not given
Freemium
Pricing
Not given
Shark Pro $5/month includes $5 of usage; Shark Studio $25/month includes $25; Shark Scale $100/month includes $100. Commands run at $0.12 per compute-hour, billed per second only while running. Services: 2 vCPU / 2 GiB at $0.03/h; 4 vCPU / 4 GiB at $0.06/h. Storage $0.08/GiB-month with first 5 GiB f
Key features
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
Persistent Space for agent files and databases
Pay only for compute time while command runs, not idle or thinking time
HTTP API with Python and TypeScript SDKs
CLI for devbox with Claude Code and Codex support
Sleeping services that wake in milliseconds
Fork Spaces fast without booting VM
API key isolation outside VM with egress proxy
Fast file search with sharkfn 300–600× faster than ripgrep
Integration with LangChain, LangGraph, smolagents, and Prefect
What makes it different
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
Billing only for seconds code actually runs, not idle or thinking time
Lowest cost compared to alternatives for agent infrastructure
Persistent Storage with fast Space fork and file access without VM boot
No GPU required, works with unmodified existing agent harnesses
Sleeping services wake in milliseconds with zero idle billing
PLCGateway AI MCP