AI agents use transform-directory to create or update resources in Mcp Nativewind — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Nativewind environment.
This tool rewrites/modifies source files in a directory by converting Tailwind components to NativeWind 4 syntax. It creates or overwrites file contents (reversible in principle if version-controlled, but the tool itself performs bulk writes). No indication of deletion, so Destructive is not warranted; Write is the most accurate category. Bulk directory-level scope raises severity to medium.
From the tool's definition Transform all components in a directory
Documented attack patterns abuse exactly the kind of access transform-directory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Nativewind, and nothing reaches the server without passing your rules. This is the rule we recommend for transform-directory:
{
"version": "1",
"default": "deny",
"tools": {
"transform-directory": {
"limits": [
{
"counter": "transform-directory_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}transform-directory 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.
Free to start. No card required.
Transform all components in a directory. It is categorised as a Write tool in the Mcp Nativewind MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Nativewind MCP server in PolicyLayer and add a rule for transform-directory: 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 Mcp Nativewind. Nothing to install.
transform-directory 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 transform-directory 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 transform-directory. 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.
transform-directory is provided by the Mcp Nativewind MCP server (tokenizin-agency/mcp-nativewind). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Nativewind, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 Mcp Nativewind tools catalogued and risk-classified — across an index of 43,000+ MCP servers.