get_message
Get a single message by id, including attachment metadata. Use read_attachment to read attachment contents.
This record as markdown: /tools/dev-agenticemail-mcp/get-message.md
What get_message does on AgenticEmail
AI agents call get_message to retrieve information from AgenticEmail without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
inbox_id | string | Yes | |
message_id | string | Yes |
Parameters from the server's own tool schema.
Why get_message is rated Low
This tool queries and retrieves email message data without creating, modifying, or deleting content. However, 'medium' severity reflects that email messages may contain sensitive personal, financial, or authentication information (passwords, tokens, PII), creating moderate blast radius if an AI agent retrieves unauthorized messages. Confidence is high because the description explicitly states retrieval behavior.
From the tool's definition Tool retrieves 'a single message by id, including attachment metadata' with no modification or deletion capability—core Read operation. Related tools (read_attachment, list_messages, list_threads) confirm the Read-only pattern of this server.
Attacks that exploit this kind of access
The rule that runs get_message safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AgenticEmail, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_message, this is the rule to start with:
get_message is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect AgenticEmail, apply this rule, and every get_message call is checked against it from then on.
Questions about get_message
Get a single message by id, including attachment metadata. Use read_attachment to read attachment contents. It is categorised as a Read tool in the AgenticEmail MCP Server, which means it retrieves data without modifying state.
get_message accepts 2 parameters: inbox_id, message_id. Required: inbox_id, message_id. The full parameter table on this page comes from the server's own tool schema.
Register the AgenticEmail MCP server in PolicyLayer and add a rule for get_message: 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 AgenticEmail. Nothing to install.
get_message 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_message 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_message. 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_message is provided by the AgenticEmail MCP server (https://api.agenticemail.dev/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on AgenticEmail, and thousands of servers like it.
This server
Across the catalogue