image_blend · farshid-mcp-imageProcessing MCP: Risk & Policy

WHAT IT DOES

What image_blend does on farshid-mcp-imageProcessing

AI agents use image_blend to create or update resources in farshid-mcp-imageProcessing — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your farshid-mcp-imageProcessing environment.

WHY IT NEEDS A POLICY

Why image_blend needs a policy

This tool creates a new output image by combining two input images using a weighted blend formula. It produces/writes a new image artifact. It does not delete or overwrite source images, execute code, or involve financial transactions. Severity is medium because misuse could overwrite important image files depending on how the output is handled.

From the tool's definition Blend two same-size images: out = a*img1 + (1-a)*img2

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

image_blend Rate-limited

image_blend 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "image_blend": {
      "limits": [
        {
          "counter": "image_blend_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches farshid-mcp-imageProcessing, so you can run agents against it safely.

FAQ

Questions about image_blend

What does the image_blend tool do? +

Blend two same-size images: out = a*img1 + (1-a)*img2. It is categorised as a Write tool in the farshid-mcp-imageProcessing MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on image_blend? +

Register the farshid-mcp-imageProcessing MCP server in PolicyLayer and add a rule for image_blend: 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 farshid-mcp-imageProcessing. Nothing to install.

What risk level is image_blend? +

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

Can I rate-limit image_blend? +

Yes. Add a rate_limit block to the image_blend 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 image_blend completely? +

Set action: deny in the PolicyLayer policy for image_blend. 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 image_blend? +

image_blend is provided by the farshid-mcp-imageProcessing MCP server (pirahansiah/farshid-mcp-imageprocessing). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.