scaffold_app
Create a new Avalanche dapp from a template (minimal, nft-mint, token-gated-app, erc20-token, icm-messenger, eerc-token, l1-launch, token-bridge). Wraps create-avalanche-app. Returns the created files and next steps.
This record as markdown: /tools/dev-avakit-avalanche/scaffold-app.md
What scaffold_app does on Avalanche
AI agents use scaffold_app to create or update resources in Avalanche, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Avalanche environment.
Why scaffold_app is rated Medium
Generates new application files and project structure; reversible through deletion but alters local environment.
From the tool's definition Create a new Avalanche dapp from a template, wraps create-avalanche-app, returns created files.
Attacks that exploit this kind of access
The rule that runs scaffold_app safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Avalanche, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For scaffold_app, this is the rule to start with:
scaffold_app stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Avalanche, apply this rule, and every scaffold_app call is checked against it from then on.
Questions about scaffold_app
Create a new Avalanche dapp from a template (minimal, nft-mint, token-gated-app, erc20-token, icm-messenger, eerc-token, l1-launch, token-bridge). Wraps create-avalanche-app. Returns the created files and next steps. It is categorised as a Write tool in the Avalanche MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Avalanche MCP server in PolicyLayer and add a rule for scaffold_app: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Avalanche. Nothing to install.
scaffold_app is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the scaffold_app rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for scaffold_app. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
scaffold_app is provided by the Avalanche MCP server (@avakit/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Avalanche, and thousands of servers like it.
This server
Across the catalogue