Remesh and optimize an existing 3D model.
AI agents use create_remesh_task to create or update resources in Meshy AI MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Meshy AI MCP Server environment.
Remeshing is a model modification operation that alters geometry while preserving the underlying asset. It is reversible (the original can typically be restored from backups or re-imported), differs from destructive deletion, and does not execute arbitrary code or trigger external side effects beyond the intended 3D model transformation.
From the tool's definition Tool name 'create_remesh_task' and description 'Remesh and optimize an existing 3D model' indicate the tool modifies an existing 3D model through remeshing and optimization operations, which are reversible transformations.
Documented attack patterns abuse exactly the kind of access create_remesh_task gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Meshy AI MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for create_remesh_task:
{
"version": "1",
"default": "deny",
"tools": {
"create_remesh_task": {
"limits": [
{
"counter": "create_remesh_task_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}create_remesh_task 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.
Remesh and optimize an existing 3D model. It is categorised as a Write tool in the Meshy AI MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Meshy AI MCP Server MCP server in PolicyLayer and add a rule for create_remesh_task: 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 Meshy AI MCP Server. Nothing to install.
create_remesh_task 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_remesh_task 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_remesh_task. 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_remesh_task is provided by the Meshy AI MCP Server MCP server (pasie15/meshy-ai-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 51 Meshy AI MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
51 Meshy AI MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.