Download and return the local path to a specific artifact
AI agents call get_run_artifact to retrieve information from MLflow MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and downloads an artifact, providing access to existing data without creating, modifying, deleting, or executing anything. This is a straightforward read operation. The severity is low because downloading an artifact does not modify state, execute code, or affect system integrity. Confidence is high because the description clearly indicates a retrieval-only function.
From the tool's definition Tool description states 'Download and return the local path to a specific artifact' — a retrieval operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access get_run_artifact 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 get_run_artifact:
{
"version": "1",
"default": "deny",
"tools": {
"get_run_artifact": {}
}
}get_run_artifact is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Download and return the local path to a specific artifact. It is categorised as a Read tool in the MLflow MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MLflow MCP Server MCP server in PolicyLayer and add a rule for get_run_artifact: 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.
get_run_artifact is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_run_artifact 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 get_run_artifact. 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.
get_run_artifact 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.