Medium Risk

upload_image

Upload an image to persistent storage for use in markdown content. Accepts either a file path or base64-encoded image data. Returns a URL that can be used in markdown images like ![alt](/images/filename.png).

How to control upload_image ↓

What upload_image does on Pane

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

Medium Risk

Why upload_image needs a policy

This tool creates new image files in persistent storage, making it a Write operation. It is reversible (images can be deleted later) and does not execute arbitrary code, delete data, move money, or trigger external operations with unpredictable effects.

From the tool's definition The tool description states it 'Upload[s] an image to persistent storage' and 'Returns a URL', indicating creation and storage of data. The verb 'upload' and explicit mention of 'persistent storage' confirm a write operation that creates or modifies data.

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

How to control upload_image

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

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

upload_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.

  1. Create a free account and register Pane — 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 upload_image

What does the upload_image tool do? +

Upload an image to persistent storage for use in markdown content. Accepts either a file path or base64-encoded image data. Returns a URL that can be used in markdown images like ![alt](/images/filename.png). It is categorised as a Write tool in the Pane MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on upload_image? +

Register the Pane MCP server in PolicyLayer and add a rule for upload_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 Pane. Nothing to install.

What risk level is upload_image? +

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

Can I rate-limit upload_image? +

Yes. Add a rate_limit block to the upload_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.

How do I block upload_image completely? +

Set action: deny in the PolicyLayer policy for upload_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.

What MCP server provides upload_image? +

upload_image is provided by the Pane MCP server (zabaca/pane). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Pane tool call.

Start from Pane, 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.

15 Pane 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.