Add a new function to an existing file. Appends at the end.
AI agents use script_add_function to create or update resources in Gworkspace — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gworkspace environment.
This tool modifies code by adding functions to existing files, which is a reversible Write operation. While it could potentially introduce malicious code if misused by an AI agent (especially given Apps Script's capability to access Google Workspace data and trigger external operations), the tool itself is fundamentally a Write operation—it appends content rather than executing it.
From the tool's definition Tool description states 'Add a new function to an existing file. Appends at the end.' - this is a modification operation that creates new code within an existing Apps Script file.
Attacks that exploit this kind of access
Add a new function to an existing file. Appends at the end. It is categorised as a Write tool in the Gworkspace MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gworkspace MCP server in PolicyLayer and add a rule for script_add_function: 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 Gworkspace. Nothing to install.
script_add_function 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 script_add_function 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 script_add_function. 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.
script_add_function is provided by the Gworkspace MCP server (leoonic/gworkspace-mcp). 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 →