AI agents call plan to retrieve information from Python without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool explicitly states it is read-only and does not modify infrastructure. It only displays what changes would be made without actually applying them, making it a pure read/query operation.
From the tool's definition Shows the Terraform execution plan with resource change counts. Read-only — does not modify infrastructure.
Attacks that exploit this kind of access
Shows the Terraform execution plan with resource change counts. Read-only — does not modify infrastructure. It is categorised as a Read tool in the Python MCP Server, which means it retrieves data without modifying state.
Register the Python MCP server in PolicyLayer and add a rule for plan: 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 Python. Nothing to install.
plan 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 plan 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 plan. 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.
plan is provided by the Python MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
plan is one line of Python'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 →