Get status of a training run (auto-analyzes errors with Codex if available)
AI agents call train_status to retrieve information from ML Lab MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports the current state of an existing training run. It performs no side effects, does not modify training configurations or data, does not execute new training steps, and does not delete or create resources. Status queries are classic Read category operations. The mention of error analysis by Codex is passive reporting, not active code execution or resource manipulation by this tool itself.
From the tool's definition Tool name is 'train_status' and description states 'Get status of a training run' - a retrieval operation with no modification or execution of training processes.
Attacks that exploit this kind of access
Get status of a training run (auto-analyzes errors with Codex if available). It is categorised as a Read tool in the ML Lab MCP MCP Server, which means it retrieves data without modifying state.
Register the ML Lab MCP server in PolicyLayer and add a rule for train_status: 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 ML Lab MCP. Nothing to install.
train_status 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 train_status 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 train_status. 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.
train_status is provided by the ML Lab MCP server (pushpullcommitpush/ml-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →