asset_gen_placeholder
Write a deterministic, in-engine PROCEDURAL placeholder asset to a res:// path — no model, fully reproducible (colour/frequency/size derive from a hash of the prompt). Always available regardless of the configured backend. kind picks the asset (all native .tres resources that load synchronously):...
This record as markdown: /tools/breakpoint-mcp/asset-gen-placeholder.md
What asset_gen_placeholder does on Breakpoint
AI agents use asset_gen_placeholder to create or update resources in Breakpoint, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Breakpoint environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
kind | string | Yes | Asset kind: sprite | texture | icon | audio_sfx | model |
shape | string | — | Primitive for model (default box) |
width | integer | — | Image width for sprite/texture/icon (default per-kind) |
height | integer | — | Image height for sprite/texture/icon (default per-kind) |
prompt | string | — | Seed text — deterministically colours/tunes/sizes the placeholder |
confirm | boolean | — | Auto-approve this destructive action (skip the confirmation prompt) |
to_path | string | Yes | Destination res:// path; the correct extension is appended if omitted |
duration_ms | integer | — | Length in ms for audio_sfx (default 300) |
Parameters from the server's own tool schema.
Why asset_gen_placeholder is rated Medium
The tool writes/creates a new file at a specified path. While the description uses the word 'DESTRUCTIVE', the actual behavior is file creation/writing of a placeholder asset, not deletion or irreversible overwriting of existing data in the traditional destructive sense. It could overwrite an existing file at the same path, which elevates concern, but the primary action is a write/create operation.
From the tool's definition 'Write a deterministic, in-engine PROCEDURAL placeholder asset to a res:// path' and 'DESTRUCTIVE (writes a file) — gated by confirmation'
Attacks that exploit this kind of access
The rule that runs asset_gen_placeholder safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For asset_gen_placeholder, this is the rule to start with:
asset_gen_placeholder 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 Breakpoint, apply this rule, and every asset_gen_placeholder call is checked against it from then on.
Questions about asset_gen_placeholder
Write a deterministic, in-engine PROCEDURAL placeholder asset to a res:// path — no model, fully reproducible (colour/frequency/size derive from a hash of the prompt). Always available regardless of the configured backend. kind picks the asset (all native .tres resources that load synchronously): sprite/texture/icon → an ImageTexture; audio_sfx → an AudioStreamWAV; model → a BoxMesh/primitive mesh. DESTRUCTIVE (writes a file) — gated by confirmation. It is categorised as a Write tool in the Breakpoint MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
asset_gen_placeholder accepts 8 parameters: kind, shape, width, height, prompt, confirm, to_path, duration_ms. Required: kind, to_path. The full parameter table on this page comes from the server's own tool schema.
Register the Breakpoint MCP server in PolicyLayer and add a rule for asset_gen_placeholder: 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 Breakpoint. Nothing to install.
asset_gen_placeholder 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 asset_gen_placeholder 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 asset_gen_placeholder. 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.
asset_gen_placeholder is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Breakpoint, and thousands of servers like it.
This server
Across the catalogue