Low Risk

getAttachment

getAttachment

How to control getAttachment ↓

AI agents call getAttachment to retrieve information from Mail MCP Tool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

getAttachment retrieves attachment data from emails without modification or deletion. While classified as Read (no side effects), severity is medium rather than low because attachments may contain sensitive information (credentials, financial data, personal documents), and an AI agent could exfiltrate confidential data.

From the tool's definition Tool name 'getAttachment' indicates data retrieval. Server description states the tool 'enables AI models to access email services' and handle 'attachments'. The tool is grouped with other Read operations like 'getEmailDetail', 'listEmails', and 'getContacts'.

Documented attack patterns abuse exactly the kind of access getAttachment gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and Mail MCP Tool, and nothing reaches the server without passing your rules. This is the rule we recommend for getAttachment:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "getAttachment": {}
  }
}

getAttachment is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Mail MCP Tool — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the getAttachment tool do? +

getAttachment. It is categorised as a Read tool in the Mail MCP Tool MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on getAttachment? +

Register the Mail MCP Tool MCP server in PolicyLayer and add a rule for getAttachment: 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 Mail MCP Tool. Nothing to install.

What risk level is getAttachment? +

getAttachment is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit getAttachment? +

Yes. Add a rate_limit block to the getAttachment 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.

How do I block getAttachment completely? +

Set action: deny in the PolicyLayer policy for getAttachment. 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.

What MCP server provides getAttachment? +

getAttachment is provided by the Mail MCP Tool MCP server (shuakami/mcp-mail). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mail MCP Tool tool call.

Deterministic rules across all 17 Mail MCP Tool tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

17 Mail MCP Tool tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.