AI agents use update_script to create or update resources in MCPMake — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCPMake environment.
This tool modifies existing script metadata and schemas reversibly. While it doesn't execute code or delete scripts, it changes the configuration and analysis of scripts, which can affect subsequent executions. It falls under Write rather than Execute because the tool itself performs analysis/metadata updates, not code execution.
From the tool's definition Tool name is 'update_script' and description states 'Re-analyze a script to update its schema and metadata', indicating modification of script metadata and schema definitions without deletion or execution of the script itself.
Attacks that exploit this kind of access
Re-analyze a script to update its schema and metadata. It is categorised as a Write tool in the MCPMake MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCPMake 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 MCPMake. 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 MCPMake MCP server (shex1627/mcpmake). 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 →