Updates an existing variable
AI agents use edit-variable to create or update resources in Terrakube MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Terrakube MCP Server environment.
This tool modifies existing infrastructure variables but does not delete or destroy them. The operation is reversible—edited values can be changed again. While it could impact infrastructure if misconfigured, it falls under Write category as a data modification action rather than Execute (which would run code) or Destructive (which cannot be undone).
From the tool's definition Tool name 'edit-variable' and description 'Updates an existing variable' indicate modification of existing data in a reversible manner.
Attacks that exploit this kind of access
Updates an existing variable. It is categorised as a Write tool in the Terrakube MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Terrakube MCP Server MCP server in PolicyLayer and add a rule for edit-variable: 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 Terrakube MCP Server. Nothing to install.
edit-variable 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 edit-variable 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 edit-variable. 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.
edit-variable is provided by the Terrakube MCP Server MCP server (terrakube-io/mcp-server-terrakube). 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 →