Download a message attachment to local disk. The fileUrl comes from a
AI agents use download_attachment to create or update resources in Rocket Cli — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rocket Cli environment.
This tool fetches remote data (Read aspect) but its primary effect is writing a file to local disk, which is a persistent side effect. It is reversible (the file can be deleted), so Write is the most appropriate category. Severity is medium because an agent could download malicious or sensitive content to the local system, but it does not delete or execute anything.
From the tool's definition 'Download a message attachment to local disk' — writes a file to the local filesystem
Attacks that exploit this kind of access
Download a message attachment to local disk. The fileUrl comes from a. It is categorised as a Write tool in the Rocket Cli MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rocket Cli MCP server in PolicyLayer and add a rule for download_attachment: 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 Rocket Cli. Nothing to install.
download_attachment 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 download_attachment 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 download_attachment. 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.
download_attachment is provided by the Rocket Cli MCP server (jeanfbrito/rocket-cli). 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 →