get_email
AI agents call get_email to retrieve information from Microsoft MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the 'get_' prefix is a standard convention for read operations. The tool retrieves email data from Outlook without modifying state. While the server as a whole supports dangerous operations, this specific tool appears limited to querying/fetching email content. Confidence is moderately high (0.90) due to lack of explicit description, but the naming convention provides strong evidence.
From the tool's definition Tool name 'get_email' with no description provided; sibling tools include destructive operations (delete_email, delete_contact, delete_event) and write operations (create_email_draft, create_event, create_file), indicating this server performs both retrieval…
Attacks that exploit this kind of access
get_email. It is categorised as a Read tool in the Microsoft MCP MCP Server, which means it retrieves data without modifying state.
Register the Microsoft MCP server in PolicyLayer and add a rule for get_email: 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 MCP. Nothing to install.
get_email 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 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. 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 is provided by the Microsoft MCP server (purva-kashyap/microsoft-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 →