Create a 3D model from an image using the Tripo API. IMPORTANT: This tool initiates a 3D model generation task but does NOT wait for completion. After calling this tool, you MUST repeatedly call the get_task_status tool with the returned task_id until the task status is SUCCESS or a terminal erro...
AI agents use create_3d_model_from_image to create or update resources in Tripo MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tripo MCP Server environment.
This tool creates a new 3D asset by submitting an image to the Tripo API for processing. It writes/creates new data (a 3D model) on an external service. It is reversible in the sense that the generated asset can be deleted, so it falls under Write rather than Destructive.
From the tool's definition Create a 3D model from an image using the Tripo API... initiates a 3D model generation task
Documented attack patterns abuse exactly the kind of access create_3d_model_from_image gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tripo MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_3d_model_from_image:
{
"version": "1",
"default": "deny",
"tools": {
"create_3d_model_from_image": {
"limits": [
{
"counter": "create_3d_model_from_image_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_3d_model_from_image 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.
Create a 3D model from an image using the Tripo API. IMPORTANT: This tool initiates a 3D model generation task but does NOT wait for completion. After calling this tool, you MUST repeatedly call the get_task_status tool with the returned task_id until the task status is SUCCESS or a terminal error state. Typical workflow: 1. Call create_3d_model_from_image to start the task 2. Get the task_id from the response 3. Call get_task_status with the task_id 4. If status is not SUCCESS, wait a moment and call get_task_status again 5. Repeat until status is SUCCESS or a terminal error state 6. When status is SUCCESS, use the pbr_model_url from the response Args: image: The local path or url to the image file. face_limit: The maximum number of faces in the model. auto_size: Whether to automatically size the model. Returns: A dictionary containing the task ID and instructions for checking the status. It is categorised as a Write tool in the Tripo MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tripo MCP Server MCP server in PolicyLayer and add a rule for create_3d_model_from_image: 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 Tripo MCP Server. Nothing to install.
create_3d_model_from_image 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 create_3d_model_from_image 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 create_3d_model_from_image. 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.
create_3d_model_from_image is provided by the Tripo MCP Server MCP server (vast-ai-research/tripo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 16 Tripo MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
16 Tripo MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.