browser_file_upload
AI agents invoke browser_file_upload to trigger actions in Playwright MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Based on the tool name, this performs a file upload action in a browser context. It triggers an external browser operation (uploading a file to a web form/endpoint), which constitutes executing a browser action with side effects. Misuse could result in sensitive local files being uploaded to arbitrary web destinations, making severity high. Confidence is reduced due to empty description.
From the tool's definition Tool name 'browser_file_upload' on a Playwright browser automation server. Description is empty/uninformative.
Attacks that exploit this kind of access
browser_file_upload. It is categorised as a Execute tool in the Playwright MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
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 Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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 (naumana3services-maker/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 →