Plot inliers and outliers and save plot.
AI agents use plot_results to create or update resources in MCP Autonomous Analyst — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Autonomous Analyst environment.
The tool creates a visualization artifact and writes it to disk. While this modifies the filesystem, it is reversible (plots can be deleted or overwritten), so it falls under Write rather than Destructive. The severity is medium because uncontrolled plot generation could consume disk space or overwrite important visualizations, but the impact is bounded and non-financial.
From the tool's definition The tool description states 'save plot', which involves creating and persisting data (the plot file) to storage. This is a reversible write operation.
Attacks that exploit this kind of access
Plot inliers and outliers and save plot. It is categorised as a Write tool in the MCP Autonomous Analyst MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Autonomous Analyst MCP server in PolicyLayer and add a rule for plot_results: 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 MCP Autonomous Analyst. Nothing to install.
plot_results 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 plot_results 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 plot_results. 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.
plot_results is provided by the MCP Autonomous Analyst MCP server (madmando/mcp-autonomous-analyst). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
plot_results is one line of MCP Autonomous Analyst's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →