Runs Vite production build and returns structured output files with sizes.
AI agents invoke vite-build to trigger actions in Http. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This is an Execute risk because it invokes an external build tool that can run arbitrary build scripts, plugins, and transformations defined in vite.config.js or package.json. A malicious agent could inject build-time code execution, modify build outputs, or exfiltrate data during the build process.
From the tool's definition The tool "Runs Vite production build" indicates execution of a build system that compiles and bundles code. This triggers external operations (the Vite build process) whose effects depend on arguments and configuration.
Documented attack patterns abuse exactly the kind of access vite-build gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Http, and nothing reaches the server without passing your rules. This is the rule we recommend for vite-build:
{
"version": "1",
"default": "deny",
"tools": {
"vite-build": {
"limits": [
{
"counter": "vite-build_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}vite-build stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Runs Vite production build and returns structured output files with sizes. It is categorised as a Execute tool in the Http MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Http MCP server in PolicyLayer and add a rule for vite-build: 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 Http. Nothing to install.
vite-build is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the vite-build 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 vite-build. 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.
vite-build is provided by the Http MCP server (@paretools/http). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Http, 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.
202 Http tools catalogued and risk-classified — across an index of 43,000+ MCP servers.