AI agents call get_file_download_url to retrieve information from E2b without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information (a download URL) from the sandbox without creating, modifying, deleting, or executing anything. It has no side effects on the sandbox or its contents. The act of generating a URL is a read-only operation. Severity is low because it only exposes access to files already within an isolated sandbox environment, limiting blast radius.
From the tool's definition Tool name is 'get_file_download_url' and description states 'Get a download URL for a file in the sandbox' - this is a retrieval operation that generates a URL for accessing file contents without modifying the sandbox state.
Attacks that exploit this kind of access
Get a download URL for a file in the sandbox. It is categorised as a Read tool in the E2b MCP Server, which means it retrieves data without modifying state.
Register the E2b MCP server in PolicyLayer and add a rule for get_file_download_url: 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 E2b. Nothing to install.
get_file_download_url is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_file_download_url 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 get_file_download_url. 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.
get_file_download_url is provided by the E2b MCP server (yukkit/e2b-mcp-server). 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 →