AI agents use add_image to create or update resources in Powerpoint — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Powerpoint environment.
Adding an image to a presentation is a reversible modification (Write category). Severity is medium because while images can be removed, a malicious agent could embed large files, inappropriate content, or images designed to confuse or mislead in a presentation.
From the tool's definition Tool name is 'add_image' and sibling tools include 'add_chart', 'add_shape', 'add_table', 'add_textbox' which all modify presentation content.
Documented attack patterns abuse exactly the kind of access add_image gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Powerpoint, and nothing reaches the server without passing your rules. This is the rule we recommend for add_image:
{
"version": "1",
"default": "deny",
"tools": {
"add_image": {
"limits": [
{
"counter": "add_image_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_image 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.
add_image. It is categorised as a Write tool in the Powerpoint MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Powerpoint MCP server in PolicyLayer and add a rule for add_image: 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 Powerpoint. Nothing to install.
add_image 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 add_image 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 add_image. 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.
add_image is provided by the Powerpoint MCP server (juanocampo400/powerpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Powerpoint, 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.
17 Powerpoint tools catalogued and risk-classified — across an index of 43,000+ MCP servers.