Get task artifacts and outputs.
AI agents call get_task_artifacts to retrieve information from Clearml without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing artifact data from ClearML tasks without creating, modifying, or deleting any resources. It is a pure read operation with minimal blast radius if misused by an agent (it may expose sensitive model weights or training data, but cannot alter or destroy resources).
From the tool's definition Tool description states 'Get task artifacts and outputs' — a retrieval operation with no modification or side effects. The verb 'Get' and the context of retrieving artifacts (stored outputs from ML experiments) align with read-only access patterns.
Documented attack patterns abuse exactly the kind of access get_task_artifacts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Clearml, and nothing reaches the server without passing your rules. This is the rule we recommend for get_task_artifacts:
{
"version": "1",
"default": "deny",
"tools": {
"get_task_artifacts": {}
}
}get_task_artifacts 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.
Get task artifacts and outputs. It is categorised as a Read tool in the Clearml MCP Server, which means it retrieves data without modifying state.
Register the Clearml MCP server in PolicyLayer and add a rule for get_task_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 Clearml. Nothing to install.
get_task_artifacts 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_task_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.
Set action: deny in the PolicyLayer policy for get_task_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.
get_task_artifacts is provided by the Clearml MCP server (prassanna-ravishankar/clearml-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Clearml, 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.
14 Clearml tools catalogued and risk-classified — across an index of 43,000+ MCP servers.