Set a tag on a registered model (e.g. problem_type, team, framework).
AI agents use set_registered_model_tag 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.
This tool creates or modifies metadata tags on registered models, which is a reversible operation (tags can be updated or removed). It does not delete data (would be Destructive), execute arbitrary code (would be Execute), move money (would be Financial), or simply read data (would be Read).
From the tool's definition Tool sets/modifies tags on a registered model, which creates or updates metadata. The description explicitly states it can set tags like 'problem_type', 'team', 'framework' — these are additive or modifying operations on model metadata.
Documented attack patterns abuse exactly the kind of access set_registered_model_tag 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 set_registered_model_tag:
{
"version": "1",
"default": "deny",
"tools": {
"set_registered_model_tag": {
"limits": [
{
"counter": "set_registered_model_tag_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_registered_model_tag 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.
Set a tag on a registered model (e.g. problem_type, team, framework). 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 set_registered_model_tag: 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.
set_registered_model_tag 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 set_registered_model_tag 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 set_registered_model_tag. 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.
set_registered_model_tag 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.