Uploads one or more files to a file input element.
AI agents invoke file_upload to trigger actions in Brave Browser MCP Server. 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.
This tool triggers an external operation (file upload) in a browser, sending local files to a remote destination. The effects depend on which files are uploaded and to which endpoint, potentially exfiltrating sensitive local data. It spans Write and Execute categories; Execute is more appropriate given it triggers a browser-mediated operation with variable and potentially irreversible external effects.
From the tool's definition Uploads one or more files to a file input element
Attacks that exploit this kind of access
Uploads one or more files to a file input element. It is categorised as a Execute tool in the Brave Browser MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Brave Browser MCP Server MCP server in PolicyLayer and add a rule for 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 Brave Browser MCP Server. Nothing to install.
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 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 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.
file_upload is provided by the Brave Browser MCP Server MCP server (slaveofgod1/brave-browser-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 →