Download a specific attachment from an email
AI agents call get_attachment to retrieve information from ProtonMail MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and downloads email attachment data without modifying, deleting, or creating content. It is a read operation. Severity is medium rather than low because email attachments may contain sensitive personal, financial, or confidential information that could be exfiltrated if an agent misuses this tool without proper access controls or user consent.
From the tool's definition Tool name 'get_attachment' and description 'Download a specific attachment from an email' indicate retrieval of data with no side effects or modification.
Attacks that exploit this kind of access
Download a specific attachment from an email. It is categorised as a Read tool in the ProtonMail MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ProtonMail MCP Server MCP server in PolicyLayer and add a rule for get_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 ProtonMail MCP Server. Nothing to install.
get_attachment 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_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 get_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.
get_attachment is provided by the ProtonMail MCP Server MCP server (ronamosa/protonmail-pro-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 →