Redo one or more previously undone operations on an image. Parameters: - steps: Number of redo steps (default 1) - image_index: Target image index (default 0) Returns: {steps_redone}
AI agents use redo to create or update resources in Gimp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gimp environment.
The 'redo' function modifies image data by reapplying edits, placing it in the Write category rather than Read. However, severity is low because: (1) redo is a standard, predictable operation with limited blast radius, (2) it only restores previous edits rather than introducing arbitrary new ones, (3) all effects are reversible through undo, and (4) it requires prior operations to have been undone first, limiting…
From the tool's definition The tool 'redo' reverses undo operations, which restores previously made modifications to an image. This is a Write operation because it modifies image state by reapplying edit operations, but is fully reversible (can be undone again).
Documented attack patterns abuse exactly the kind of access redo gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gimp, and nothing reaches the server without passing your rules. This is the rule we recommend for redo:
{
"version": "1",
"default": "deny",
"tools": {
"redo": {
"limits": [
{
"counter": "redo_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}redo 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.
Redo one or more previously undone operations on an image. Parameters: - steps: Number of redo steps (default 1) - image_index: Target image index (default 0) Returns: {steps_redone}. It is categorised as a Write tool in the Gimp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gimp MCP server in PolicyLayer and add a rule for redo: 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 Gimp. Nothing to install.
redo 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 redo 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 redo. 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.
redo is provided by the Gimp MCP server (maorcc/gimp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gimp, 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.
79 Gimp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.