get_run_artifacts

THE RISK

Low Risk

Why get_run_artifacts needs a policy

This tool retrieves and lists artifacts associated with MLflow run objects—a read-only operation with no side effects. It does not modify, delete, execute, or create any data. While it may expose artifact metadata that could be sensitive depending on what experiments store, the tool itself is fundamentally a data retrieval operation with no capability to alter system state.

From the tool's definition Tool name 'get_run_artifacts' and description 'List artifacts for a specific run' indicate retrieval and querying of artifact metadata with no modification capability. The 'path' parameter enables navigation but retrieves data only.

Documented attack patterns abuse exactly the kind of access get_run_artifacts gives an agent:

POLICY

How to control get_run_artifacts

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_artifacts:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_run_artifacts": {}
  }
}

get_run_artifacts is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register MLflow MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MLflow MCP Server tools

Destructive delete_experiment Delete an experiment and all its runs. Moves to the 'deleted' lifecycle stage — not shown Destructive delete_model_alias Remove an alias from a registered model (e.g. revoke 'champion'). The alias is permanently Destructive delete_model_version Delete a specific model version from the registry. Irreversible — the version and its meta Destructive delete_registered_model Delete an entire registered model and all its versions. Irreversible — all versions, alias Destructive delete_run Delete a run. Moves it to the 'deleted' lifecycle stage — not shown in UI or queries, but Write transition_model_version_stage transition_model_version_stage Write copy_model_version copy_model_version Write register_model register_model

All 40 MLflow MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_run_artifacts

What does the get_run_artifacts tool do? +

List artifacts for a specific run. Use 'path' to browse into directories (e.g., 'configs'). It is categorised as a Read tool in the MLflow MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_run_artifacts? +

Register the MLflow MCP Server MCP server in PolicyLayer and add a rule for get_run_artifacts: 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.

What risk level is get_run_artifacts? +

get_run_artifacts is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_run_artifacts? +

Yes. Add a rate_limit block to the get_run_artifacts 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.

How do I block get_run_artifacts completely? +

Set action: deny in the PolicyLayer policy for get_run_artifacts. 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.

What MCP server provides get_run_artifacts? +

get_run_artifacts 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.

Enforce policy on every MLflow MCP Server tool call.

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.

CHECK YOUR STACK →