AI agents use copy_model_version to create or update resources in MLflow MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MLflow MCP Server environment.
The tool performs a model registry operation that creates or duplicates a model version. This is a Write operation—it creates new data (a copy) but is reversible (the copy can be deleted). Without an explicit description, confidence is moderate. Severity is medium because misuse could clutter the model registry or create unintended model versions, but the impact is contained to the ML tracking system and reversible.
From the tool's definition Tool named 'copy_model_version' with empty description. Based on sibling tools on MLflow MCP Server (delete_model_version, delete_registered_model, etc.) and typical MLflow model registry operations, copying a model version would create a new model artifact…
Documented attack patterns abuse exactly the kind of access copy_model_version gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MLflow MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for copy_model_version:
{
"version": "1",
"default": "deny",
"tools": {
"copy_model_version": {
"limits": [
{
"counter": "copy_model_version_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}copy_model_version 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.
copy_model_version. It is categorised as a Write tool in the MLflow MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MLflow MCP Server MCP server in PolicyLayer and add a rule for copy_model_version: 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 MLflow MCP Server. Nothing to install.
copy_model_version 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 copy_model_version 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 copy_model_version. 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.
copy_model_version is provided by the MLflow MCP Server MCP server (kkruglik/mlflow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MLflow MCP Server, 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.
40 MLflow MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.