Medium Risk

editImage

Edit or modify an existing image based on a text prompt. User-configured settings in MCP config will be used as defaults unless specifically overridden.

How to control editImage ↓

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

Medium Risk

This tool modifies image data reversibly—the original can typically be retained and the edit can be undone or replaced. It does not delete, destroy, or permanently overwrite data (which would be Destructive), nor does it execute arbitrary code or external operations (Execute). It is a Write operation that transforms media.

From the tool's definition editImage: 'Edit or modify an existing image based on a text prompt.' The tool modifies image data based on user input, creating a new version of an existing image.

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

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

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

editImage 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 MCPollinations Multimodal MCP Server — 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.

Go deeper

What does the editImage tool do? +

Edit or modify an existing image based on a text prompt. User-configured settings in MCP config will be used as defaults unless specifically overridden. It is categorised as a Write tool in the MCPollinations Multimodal MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on editImage? +

Register the MCPollinations Multimodal MCP Server MCP server in PolicyLayer and add a rule for editImage: 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 MCPollinations Multimodal MCP Server. Nothing to install.

What risk level is editImage? +

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

Can I rate-limit editImage? +

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

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

editImage is provided by the MCPollinations Multimodal MCP Server MCP server (pinkpixel-dev/mcpollinations). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCPollinations Multimodal MCP Server tool call.

Deterministic rules across all 9 MCPollinations Multimodal MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

9 MCPollinations Multimodal MCP Server tools catalogued and risk-classified — across an index of 42,500+ 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.