Your agent has hands.
Now you have eyes.
Your AI agent can change your infrastructure faster than you can read its diffs. stackcanvas is the missing supervision surface: a live local map of your Terraform estate where you see what the agent is about to do — and approve it — before it happens.
Text is a terrible supervision surface for infrastructure.
Agents made infra changes more frequent and each change less legible. A 400-line terraform plan hides the one thing that matters: what this change touches around itself. So you either slow the agent down — or rubber-stamp it.
instance_type = "t3.micro" -> "t3.large"
ebs_optimized = false -> true
~ resource "aws_lb_target_group" "app" {
deregistration_delay = 300 -> 30
health_check { interval = 30 -> 10 }
+ resource "aws_security_group_rule" "tmp" {
cidr_blocks = ["10.0.0.0/8"]
- resource "aws_db_instance" "prod" {
engine = "postgres" # DESTROYED
~ resource "aws_ecs_service" "api" {
desired_count = 2 -> 4
launch_type = "FARGATE"
+ resource "aws_cloudwatch_log_group" "api" {
retention_in_days = 14
~ resource "aws_route53_record" "www" {
ttl = 300 -> 60
You see. You draw. The agent codes.
stackcanvas is an MCP tool for AI coding agents — Claude Code is the CI-verified path; Cursor/Windsurf reported working; any MCP-capable agent should speak it. It contains zero code generators — the agent you already pay for writes all the HCL, in your repo's style.
The map lives by itself
State changes on disk → the canvas redraws over WebSocket. Plan diffs render as color: create, update, delete, replace — with attribute-level detail in the inspector.
Gestures become intent
Drag a resource from the palette, pull an edge to a node, write a wish like small, no multi-AZ. Send to agent ships a strict intent — exact addresses, zero ambiguity — straight into the agent's loop.
Nothing applies without you
The agent writes HCL, runs terraform plan, the canvas shows the diff. The canvas has no terraform-apply control — the Send-to-agent button only proposes; your agent executes, and only when you say so.
Trusting us is not required.
Every platform that can "show and steer" your infra wants your prod credentials in their cloud. stackcanvas structurally can't leak what it never has.
127.0.0.1 only
The server binds to localhost. Not "behind a login" — physically unreachable from outside. No cloud backend for your data — the only thing we run is an opt-in, allowlisted telemetry counter.
Zero credentials
It reads your local state and plan files. No AWS keys, no tokens, nothing to hand over, nothing to breach.
Secrets masked
Everything Terraform marks sensitive becomes ••• inside the parser — before it ever reaches the UI.
Agent-only execution
The canvas proposes; your agent executes. MIT-licensed, open source, opt-in anonymous telemetry — fully documented.