upload_museum_logo · Confd MCP: Risk & Policy

WHAT IT DOES

What upload_museum_logo does on Confd

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

WHY IT NEEDS A POLICY

Why upload_museum_logo needs a policy

This tool creates or modifies data reversibly—it uploads an image that can be replaced or deleted later (as evidenced by the sibling tool delete_museum_logo). While it persists data to the system, the operation is not irreversible and does not execute arbitrary code, trigger external side effects with unpredictable consequences, or involve financial transactions. It falls squarely in the Write category.

From the tool's definition upload_museum_logo uploads and stores a logo image for a museum, modifying museum data by adding/replacing an image asset.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

upload_museum_logo Rate-limited

upload_museum_logo 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": {
    "upload_museum_logo": {
      "limits": [
        {
          "counter": "upload_museum_logo_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 Confd, so you can run agents against it safely.

FAQ

Questions about upload_museum_logo

What does the upload_museum_logo tool do? +

Upload a logo image for a museum. Provide exactly one of: url (fetch from URL), base64 (base64-encoded image data), or file_path (local file path). Accepts png, jpeg, webp, gif up to 5MB. It is categorised as a Write tool in the Confd 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_museum_logo? +

Register the Confd MCP server in PolicyLayer and add a rule for upload_museum_logo: 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 Confd. Nothing to install.

What risk level is upload_museum_logo? +

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

Can I rate-limit upload_museum_logo? +

Yes. Add a rate_limit block to the upload_museum_logo 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_museum_logo completely? +

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

upload_museum_logo is provided by the Confd MCP server (mytours/confd-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.