change_directory
AI agents invoke change_directory to trigger actions in Browser Automation 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.
Changing the working directory is an execution-side-effect operation that alters the runtime environment state. While it doesn't delete data, it can affect subsequent file operations by redirecting them to a different directory, potentially causing unintended reads/writes elsewhere. The description is empty, so confidence is lowered.
From the tool's definition Tool name is 'change_directory'; description is empty or uninformative.
Attacks that exploit this kind of access
change_directory. It is categorised as a Execute tool in the Browser Automation MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Browser Automation MCP Server MCP server in PolicyLayer and add a rule for change_directory: 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 Automation MCP Server. Nothing to install.
change_directory 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 change_directory 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 change_directory. 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.
change_directory is provided by the Browser Automation MCP Server MCP server (raghu6798/browser_scrape_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 →