// MCP TOOL REFERENCE

AGENTMAIL TOOLS

11 tools from the Agentmail MCP Server, categorised by risk level.

View the Agentmail policy → Token cost: 1,398 tokens →

// ALL 11 AGENTMAIL TOOLS

READ 7 tools

Read forward_message Forward message Read get_attachment Get attachment Read get_inbox Get inbox Read get_thread Get thread Read list_inboxes List inboxes Read list_threads List threads in inbox Read reply_to_message Reply to message

WRITE 3 tools

Write create_inbox Create inbox Write send_message Send message Write update_message Update message

DESTRUCTIVE 1 tools

Destructive delete_inbox Delete inbox

// RUNNING THIS SERVER

The managed route: connect Agentmail through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y agentmail-mcp

// FAQ

How many tools does the Agentmail MCP server have? +

The Agentmail MCP server exposes 11 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Agentmail tools? +

Route the Agentmail server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Agentmail tools fall into? +

Agentmail tools are categorised as Read (7), Write (3), Destructive (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.