Compare multiple tasks by metrics.
AI agents call compare_tasks 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.
The compare_tasks tool retrieves and compares metric data from existing tasks. It does not create, modify, delete, or execute code. The comparison is a read-only analytical operation that has no side effects on the tasks or their data. This is a straightforward information retrieval pattern.
From the tool's definition Tool description states 'Compare multiple tasks by metrics' — a retrieval and analysis operation with no modification or execution of tasks.
Documented attack patterns abuse exactly the kind of access compare_tasks 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 compare_tasks:
{
"version": "1",
"default": "deny",
"tools": {
"compare_tasks": {}
}
}compare_tasks 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.
Compare multiple tasks by metrics. 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 compare_tasks: 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.
compare_tasks 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 compare_tasks 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 compare_tasks. 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.
compare_tasks 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.