upload_and_generate
AI agents use upload_and_generate to create or update resources in Worldlabs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Worldlabs environment.
This tool uploads user content and generates 3D world assets, which are reversible write operations. It doesn't delete (Destructive), execute arbitrary code (Execute), or handle financial transactions (Financial). However, it ranks high severity because unsupervised uploads could fill storage, generate malicious 3D content, or create unauthorized worlds.
From the tool's definition Tool name 'upload_and_generate' indicates file upload and generation operations. Sibling tools show this server creates and manages world assets (generate_world_from_*), and includes delete_world which is destructive.
Documented attack patterns abuse exactly the kind of access upload_and_generate gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Worldlabs, and nothing reaches the server without passing your rules. This is the rule we recommend for upload_and_generate:
{
"version": "1",
"default": "deny",
"tools": {
"upload_and_generate": {
"limits": [
{
"counter": "upload_and_generate_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} upload_and_generate 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.
upload_and_generate. It is categorised as a Write tool in the Worldlabs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Worldlabs MCP server in PolicyLayer and add a rule for upload_and_generate: 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 Worldlabs. Nothing to install.
upload_and_generate 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 upload_and_generate 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 upload_and_generate. 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.
upload_and_generate is provided by the Worldlabs MCP server (sandraschi/worldlabs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Worldlabs, 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.
20 Worldlabs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.