submit_pack
Group 2–50 of the user’s own uploads (any that are processing, pending or published) into a pack proposal. Upload the models first with finalize_upload or submit_asset_from_url, then pass their slugs here. Each model is still reviewed on its own; a person approves the pack as a whole, which publi...
This record as markdown: /tools/3dassets-mcp/submit-pack.md
What submit_pack does on 3dassets
AI agents use submit_pack to create or update resources in 3dassets, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 3dassets environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
title | string | Yes | |
assets | array | Yes | |
summary | string | Yes | |
description | string | — |
Parameters from the server's own tool schema.
Why submit_pack is rated Medium
An AI agent can call submit_pack faster than any human can review: one bad instruction and it creates or modifies resources in 3dassets by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs submit_pack safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 3dassets, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For submit_pack, this is the rule to start with:
submit_pack 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 3dassets, apply this rule, and every submit_pack call is checked against it from then on.
Questions about submit_pack
Group 2–50 of the user’s own uploads (any that are processing, pending or published) into a pack proposal. Upload the models first with finalize_upload or submit_asset_from_url, then pass their slugs here. Each model is still reviewed on its own; a person approves the pack as a whole, which publishes any members still pending and creates the pack page. Nothing goes live until then. The user is emailed the outcome. It is categorised as a Write tool in the 3dassets MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
submit_pack accepts 4 parameters: title, assets, summary, description. Required: title, assets, summary. The full parameter table on this page comes from the server's own tool schema.
Register the 3dassets MCP server in PolicyLayer and add a rule for submit_pack: 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 3dassets. Nothing to install.
submit_pack 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 submit_pack 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 submit_pack. 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.
submit_pack is provided by the 3dassets MCP server (3dassets-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 3dassets, and thousands of servers like it.
This server
Across the catalogue