clean_dataset
Clean and preprocess a dataset. Returns path to cleaned CSV and action summary.
This record as markdown: /tools/agentic-automl-platform/clean-dataset.md
What clean_dataset does on Agentic Automl Platform
AI agents use clean_dataset to create or update resources in Agentic Automl Platform, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agentic Automl Platform environment.
Why clean_dataset is rated Medium
The tool modifies the dataset by cleaning and preprocessing it, then writes the result to a new CSV file. This is a data transformation/write operation — it creates a new artifact (cleaned CSV) but does not irreversibly destroy the original dataset. Misuse could corrupt ML pipeline inputs, hence medium severity.
From the tool's definition 'Clean and preprocess a dataset. Returns path to cleaned CSV and action summary.'
Attacks that exploit this kind of access
The rule that runs clean_dataset 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 clean_dataset, this is the rule to start with:
clean_dataset stays usable, but capped: an agent stuck in a loop can't make hundreds of changes 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 clean_dataset call is checked against it from then on.
Questions about clean_dataset
Clean and preprocess a dataset. Returns path to cleaned CSV and action summary. It is categorised as a Write tool in the Agentic Automl Platform MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Agentic Automl Platform MCP server in PolicyLayer and add a rule for clean_dataset: 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.
clean_dataset is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the clean_dataset 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 clean_dataset. 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.
clean_dataset 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.
This server
Across the catalogue