This record as markdown: /tools/mcp-dev/update-script.md
What update-script does on Mcp Dev
AI agents use update-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.
Why update-script is rated Medium
The tool modifies (not deletes) script files, placing it in Write category. Severity is high because updating scripts in a CMS can have broad runtime consequences—malicious script changes could compromise site functionality, inject malicious code, or alter business logic. However, it is reversible (scripts can be updated again), so it does not reach Destructive or Execute severity.
From the tool's definition Tool name 'update-script' and description 'Updates a script by path' indicate modification of script files, which are executable code artifacts in a CMS environment.
Attacks that exploit this kind of access
The rule that runs update-script safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Dev, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For update-script, this is the rule to start with:
update-script 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 Mcp Dev, apply this rule, and every update-script call is checked against it from then on.
Questions about update-script
Updates a script by 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 update-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.
update-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 update-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 update-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.
update-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.
More on Mcp Dev, and thousands of servers like it.
This server
Across the catalogue