List files and folders at a WebDAV path on Fastmail Files.
AI agents call files_list 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 queries and retrieves file/folder metadata from Fastmail's WebDAV storage without creating, modifying, deleting, or executing any actions. It is a straightforward read operation with no side effects. The blast radius is minimal—an AI agent querying file listings cannot cause data loss or financial harm, only information disclosure of files the authenticated user already has access to.
From the tool's definition Tool name 'files_list' and description 'List files and folders at a WebDAV path' indicates retrieval of directory contents without modification or deletion.
Attacks that exploit this kind of access
List files and folders at a WebDAV path on Fastmail Files. 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_list: 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_list 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_list 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_list. 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_list 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 →