Medium Risk

uploadFiles

Upload files through a file input element

How to control uploadFiles ↓

What uploadFiles does on PlayMCP Browser Automation Server

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

Medium Risk

Why uploadFiles needs a policy

File uploading is a Write-category operation as it creates or modifies data (files on a remote server) in a reversible manner. Severity is medium because: (1) the actual impact depends entirely on which file input element is targeted and what server processes the upload, (2) it could potentially introduce malware or malicious content if misused by an agent, but (3) uploaded files are typically manageable/deletable.

From the tool's definition Tool uploads files through a file input element; described as uploading files which creates or modifies data on a target system. The context shows this is part of a browser automation server that can interact with web forms and elements.

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

How to control uploadFiles

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

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

uploadFiles 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 PlayMCP Browser Automation 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.

Related tools and policies

Go deeper

Questions about uploadFiles

What does the uploadFiles tool do? +

Upload files through a file input element. It is categorised as a Write tool in the PlayMCP Browser Automation 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 uploadFiles? +

Register the PlayMCP Browser Automation Server MCP server in PolicyLayer and add a rule for uploadFiles: 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 PlayMCP Browser Automation Server. Nothing to install.

What risk level is uploadFiles? +

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

Can I rate-limit uploadFiles? +

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

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

uploadFiles is provided by the PlayMCP Browser Automation Server MCP server (jomon003/playmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every PlayMCP Browser Automation Server tool call.

Start from PlayMCP Browser Automation Server, 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.

38 PlayMCP Browser Automation Server 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.