Read the content of an email attachment. Automatically parses PDF, Word, Excel, PowerPoint, CSV, and HTML into readable text. Text files are returned as-is. Binary files return metadata only (no base64 dumps). Max 20 MB. Pass attachment_id from a mail_get_message response, or omit it to auto-sele...
AI agents call mail_get_attachment to retrieve information from M365 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and parses attachment content without creating, modifying, deleting, or executing any operations. It is a read-only retrieval function. Severity is elevated to medium (rather than low) because email attachments can contain sensitive information (credentials, financial data, personal details, intellectual property), and automated parsing without explicit user context could expose such data to AI…
From the tool's definition Tool performs 'Read the content of an email attachment' with automatic parsing of various document formats into readable text. Returns content without modification or side effects.
Attacks that exploit this kind of access
Read the content of an email attachment. Automatically parses PDF, Word, Excel, PowerPoint, CSV, and HTML into readable text. Text files are returned as-is. Binary files return metadata only (no base64 dumps). Max 20 MB. Pass attachment_id from a mail_get_message response, or omit it to auto-select when the message has a single attachment (if there are several, the tool returns the list to choose from). It is categorised as a Read tool in the M365 MCP Server, which means it retrieves data without modifying state.
Register the M365 MCP server in PolicyLayer and add a rule for mail_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 M365. Nothing to install.
mail_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 mail_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 mail_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.
mail_get_attachment is provided by the M365 MCP server (swamirama/m365-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 →