open_email · Eml MCP: Risk & Policy

WHAT IT DOES

What open_email does on Eml

AI agents invoke open_email to trigger actions in Eml. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why open_email needs a policy

This tool triggers an external application (the default mail client) to open a file, which constitutes executing an external operation. It doesn't merely read/return data to the AI — it launches a GUI application with side effects (opening a window, potentially marking mail as read, triggering mail client behaviors). This places it in Execute rather than Read.

From the tool's definition Open an existing .eml file in the default mail client

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

open_email Rate-limited

open_email stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "open_email": {
      "limits": [
        {
          "counter": "open_email_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Eml, so you can run agents against it safely.

FAQ

Questions about open_email

What does the open_email tool do? +

Open an existing .eml file in the default mail client. Use search_emails to find the filePath first. It is categorised as a Execute tool in the Eml MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on open_email? +

Register the Eml MCP server in PolicyLayer and add a rule for open_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 Eml. Nothing to install.

What risk level is open_email? +

open_email is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit open_email? +

Yes. Add a rate_limit block to the open_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.

How do I block open_email completely? +

Set action: deny in the PolicyLayer policy for open_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.

What MCP server provides open_email? +

open_email is provided by the Eml MCP server (miguelripoll23/eml-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.