Resize an embedded image by updating its EMU extent attributes.
AI agents use set_image_size to create or update resources in Docx — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Docx environment.
This tool modifies document structure reversibly by altering image dimensions. It does not execute code, trigger external operations, or irreversibly delete data. The change is editable/undoable, making it a Write action rather than Execute or Destructive. Severity is medium because misuse could corrupt document layout or render images unusable, but the effect is contained to a single image property and reversible.
From the tool's definition Tool description states it "Resize[s] an embedded image by updating its EMU extent attributes" — this modifies document content via dimension changes to embedded objects.
Documented attack patterns abuse exactly the kind of access set_image_size gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Docx, and nothing reaches the server without passing your rules. This is the rule we recommend for set_image_size:
{
"version": "1",
"default": "deny",
"tools": {
"set_image_size": {
"limits": [
{
"counter": "set_image_size_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}set_image_size 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.
Free to start. No card required.
Resize an embedded image by updating its EMU extent attributes. It is categorised as a Write tool in the Docx MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Docx MCP server in PolicyLayer and add a rule for set_image_size: 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 Docx. Nothing to install.
set_image_size 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 set_image_size 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 set_image_size. 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.
set_image_size is provided by the Docx MCP server (securityronin/docx-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Docx, 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.
219 Docx tools catalogued and risk-classified — across an index of 43,000+ MCP servers.