train_model
Train a model on a cleaned dataset. Logs to MLflow. Returns train metrics and run_id.
This record as markdown: /tools/agentic-automl-platform/train-model.md
What train_model does on Agentic Automl Platform
AI agents invoke train_model to trigger actions in Agentic Automl Platform. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why train_model is rated High
Training a model executes a computational process, triggers external MLflow logging, and produces persistent artifacts (model runs/run_id). It is not a simple read or write of user data, but an execution of a potentially long-running ML training job with side effects on an external tracking system (MLflow). No destructive, financial, or purely read behavior is indicated.
From the tool's definition Train a model on a cleaned dataset. Logs to MLflow. Returns train metrics and run_id.
Attacks that exploit this kind of access
The rule that runs train_model safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Agentic Automl Platform, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For train_model, this is the rule to start with:
train_model stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Agentic Automl Platform, apply this rule, and every train_model call is checked against it from then on.
Questions about train_model
Train a model on a cleaned dataset. Logs to MLflow. Returns train metrics and run_id. It is categorised as a Execute tool in the Agentic Automl Platform MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Agentic Automl Platform MCP server in PolicyLayer and add a rule for train_model: 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 Agentic Automl Platform. Nothing to install.
train_model is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the train_model 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_model. 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_model is provided by the Agentic Automl Platform MCP server (anantshri1/agentic-automl-platform). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Agentic Automl Platform, and thousands of servers like it.
Across the catalogue