Medium Risk

inpaint

Inpaint an image using a mask

How to control inpaint ↓

What inpaint does on MCP Flux Studio

AI agents use inpaint to create or update resources in MCP Flux Studio — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Flux Studio environment.

Medium Risk

Why inpaint needs a policy

Inpainting modifies an image by replacing masked areas with new content. This is a Write operation (reversible modification of data) rather than Destructive because the original image is not necessarily overwritten — a new image is typically produced. Severity is medium since misuse could alter images in unintended ways, but the blast radius is limited to image assets.

From the tool's definition 'Inpaint an image using a mask' — modifies an existing image by filling masked regions with generated content

Documented attack patterns abuse exactly the kind of access inpaint gives an agent:

How to control inpaint

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Flux Studio, and nothing reaches the server without passing your rules. This is the rule we recommend for inpaint:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "inpaint": {
      "limits": [
        {
          "counter": "inpaint_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

inpaint 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.

  1. Create a free account and register MCP Flux Studio — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about inpaint

What does the inpaint tool do? +

Inpaint an image using a mask. It is categorised as a Write tool in the MCP Flux Studio MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on inpaint? +

Register the MCP Flux Studio MCP server in PolicyLayer and add a rule for inpaint: 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 MCP Flux Studio. Nothing to install.

What risk level is inpaint? +

inpaint is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit inpaint? +

Yes. Add a rate_limit block to the inpaint 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.

How do I block inpaint completely? +

Set action: deny in the PolicyLayer policy for inpaint. 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.

What MCP server provides inpaint? +

inpaint is provided by the MCP Flux Studio MCP server (jmanhype/mcp-flux-studio). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Flux Studio tool call.

Start from MCP Flux Studio, 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.

4 MCP Flux Studio tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.