AI agents use browser_set_input_files to create or update resources in Mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp environment.
This tool writes/modifies the state of a browser form element by attaching files to it. It is a Write action as it sets data in a browser context. It does not execute code or delete data, but it could be used to upload files to external systems, which makes it medium severity.
From the tool's definition 'Attach one or more local or in-memory files to an <input type=' — the tool sets/attaches files to a file input element in a browser session
Attacks that exploit this kind of access
Attach one or more local or in-memory files to an <input type=. It is categorised as a Write tool in the Mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP server in PolicyLayer and add a rule for browser_set_input_files: 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 Mcp. Nothing to install.
browser_set_input_files 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_set_input_files 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_set_input_files. 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_set_input_files is provided by the MCP server (victormyschik/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 →