Upload one or multiple files
AI agents use browser_file_upload to create or update resources in Playwright MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Playwright MCP environment.
This tool enables an AI agent to programmatically upload files to web applications, which modifies state on remote systems. While uploads are typically reversible, the severity is high because an agent could upload malicious files, sensitive data to wrong destinations, or large quantities of unwanted files. The tool spans Write (file creation) but not Execute (no code running) or Destructive (uploads are undoable).
From the tool's definition Tool name 'browser_file_upload' and description 'Upload one or multiple files' indicate creation/modification of data on remote systems via browser automation. This is reversible (files can be deleted), distinguishing it from Destructive.
Attacks that exploit this kind of access
Upload one or multiple files. It is categorised as a Write tool in the Playwright MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Playwright MCP server in PolicyLayer and add a rule for browser_file_upload: 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 Playwright MCP. Nothing to install.
browser_file_upload is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the browser_file_upload 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.
Set action: deny in the PolicyLayer policy for browser_file_upload. 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.
browser_file_upload is provided by the Playwright MCP server (markbustamante77/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →