Upload files
AI agents use browser_file_upload to create or update resources in Browser Pool — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Browser Pool environment.
This tool uploads files to browser forms, creating or modifying data on remote servers. This is a write operation (not just read/query). However, it is not destructive (data is not deleted), not financial (no money moves), and not execute (arbitrary code execution isn't the primary purpose—file upload is).
From the tool's definition Tool name: browser_file_upload; description: Upload files. The tool uploads files to web forms, which is a write operation that modifies the state of a web application.
Attacks that exploit this kind of access
Upload files. It is categorised as a Write tool in the Browser Pool MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Browser Pool 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 Browser Pool. 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 Browser Pool MCP server (omgeverdo/browser-pool-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 →