Download a file from Fastmail Files (WebDAV), returned as base64.
AI agents call files_get to retrieve information from Pyfastmail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/downloads files from cloud storage and returns them as base64-encoded data. It has no side effects—it does not create, modify, delete, or execute anything. It is purely a read operation accessing existing data. The low severity reflects that file downloads alone pose minimal risk unless the contents are sensitive, but that is a data classification issue rather than a tool capability issue.
From the tool's definition Tool name 'files_get' and description 'Download a file from Fastmail Files (WebDAV), returned as base64' explicitly indicate data retrieval with no modification or deletion.
Attacks that exploit this kind of access
Download a file from Fastmail Files (WebDAV), returned as base64. It is categorised as a Read tool in the Pyfastmail MCP Server, which means it retrieves data without modifying state.
Register the Pyfastmail MCP server in PolicyLayer and add a rule for files_get: 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 Pyfastmail. Nothing to install.
files_get 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 files_get 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 files_get. 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.
files_get is provided by the Pyfastmail MCP server (pjosols/pyfastmail-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 →