Get full email content by cache number. Use the cache number from browse_email_cache (e.g., 1, 2, 3) to retrieve complete email with body, attachments, and all details. Returns: {success: boolean, subject: string, from: string, to: array, cc: array, bcc: array, body: string, attachments: array, s...
AI agents call get_email_content to retrieve information from Microsoft Graph 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 queries email messages—a classic Read operation with no modification of email state. Although it can download attachments to disk (write operation), the core and dominant function is data retrieval. Severity is medium because emails often contain sensitive personal, financial, or business information; unauthorized access could expose PII, trade secrets, or confidential communications.
From the tool's definition Tool 'Get full email content by cache number' retrieves email data including 'body, attachments, and all details' with 'Returns: {success: boolean, subject: string, from: string, to: array, cc: array, bcc: array, body: string, attachments: array, sent_date:…
Documented attack patterns abuse exactly the kind of access get_email_content gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Microsoft Graph MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_email_content:
{
"version": "1",
"default": "deny",
"tools": {
"get_email_content": {}
}
}get_email_content is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get full email content by cache number. Use the cache number from browse_email_cache (e.g., 1, 2, 3) to retrieve complete email with body, attachments, and all details. Returns: {success: boolean, subject: string, from: string, to: array, cc: array, bcc: array, body: string, attachments: array, sent_date: string, received_date: string}. Note: Invalid cache_number returns appropriate error message. ATTACHMENT DOWNLOAD: Set download_attachments=true to download attachments to the workspace/attachments folder. Attachments are saved with their original names. Use attachment_names to download only specific attachments. IMAGE ATTACHMENTS: When an email has image attachments (contentType starts with. It is categorised as a Read tool in the Microsoft Graph MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Microsoft Graph MCP Server MCP server in PolicyLayer and add a rule for get_email_content: 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 Microsoft Graph MCP Server. Nothing to install.
get_email_content 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_email_content 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_email_content. 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_email_content is provided by the Microsoft Graph MCP Server MCP server (marlonluo2018/microsoft_graph_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Microsoft Graph MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
19 Microsoft Graph MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.