AI agents use rename-script to create or update resources in Mcp Dev — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Dev environment.
Renaming is a write operation that alters data (the script's name/identifier) but is not destructive because it does not delete content, does not execute code, and can be undone by renaming again. In a CMS context, renaming scripts could disrupt references or automation that depend on the old name, warranting 'medium' severity; however, the core operation is metadata modification (Write category).
From the tool's definition Tool description explicitly states 'Renames a script', which modifies metadata of an existing script resource. The action is reversible—the script can be renamed again to restore the original name.
Attacks that exploit this kind of access
Renames a script by name and folder path. It is categorised as a Write tool in the Mcp Dev MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Dev MCP server in PolicyLayer and add a rule for rename-script: 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 Dev. Nothing to install.
rename-script 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 rename-script 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 rename-script. 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.
rename-script is provided by the Mcp Dev MCP server (@umbraco-cms/mcp-dev). 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 →