Execute custom InDesign ExtendScript code
AI agents invoke execute_indesign_code to trigger actions in InDesign MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool permits execution of arbitrary code within the InDesign application context. While the blast radius is limited to InDesign (not system-level shell execution), it can modify documents, access file systems, and perform irreversible operations depending on the injected script. An AI agent with malicious or misguided prompts could execute destructive ExtendScript.
From the tool's definition Tool name is 'execute_indesign_code' and description states 'Execute custom InDesign ExtendScript code'. The verb 'Execute' combined with 'custom' code capability indicates this runs arbitrary ExtendScript, which is a programming language for Adobe InDesign.
Documented attack patterns abuse exactly the kind of access execute_indesign_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and InDesign MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_indesign_code:
{
"version": "1",
"default": "deny",
"tools": {
"execute_indesign_code": {
"limits": [
{
"counter": "execute_indesign_code_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} execute_indesign_code stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute custom InDesign ExtendScript code. It is categorised as a Execute tool in the InDesign MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the InDesign MCP Server MCP server in PolicyLayer and add a rule for execute_indesign_code: 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 InDesign MCP Server. Nothing to install.
execute_indesign_code is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_indesign_code 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 execute_indesign_code. 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.
execute_indesign_code is provided by the InDesign MCP Server MCP server (zachshallbetter/indesign-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from InDesign MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
135 InDesign MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.