email_read_message

Read the full content of an email message by UID, including text and HTML body

SERVERScopeGate SOURCEhttps://mcp.scopegate.cloud/{api_key}

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-alifanov-scopegate/email-read-message.md

WHAT IT DOES

What email_read_message does on ScopeGate

AI agents call email_read_message to retrieve information from ScopeGate without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why email_read_message is rated Low

This tool retrieves email data without side effects. However, severity is medium rather than low because email messages often contain sensitive personal, financial, or confidential information (PII, credentials, business secrets). Misuse by an untrusted agent could expose significant private data, though no data is actually modified or destroyed.

From the tool's definition Tool name is 'email_read_message' and description states it 'Read[s] the full content of an email message by UID, including text and HTML body'.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs email_read_message safely

PolicyLayer is an MCP gateway: it sits between your AI agents and ScopeGate, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For email_read_message, this is the rule to start with:

email_read_message Allowed

email_read_message is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "email_read_message": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect ScopeGate, apply this rule, and every email_read_message call is checked against it from then on.

FAQ

Questions about email_read_message

What does the email_read_message tool do? +

Read the full content of an email message by UID, including text and HTML body. It is categorised as a Read tool in the ScopeGate MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on email_read_message? +

Register the ScopeGate MCP server in PolicyLayer and add a rule for email_read_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 ScopeGate. Nothing to install.

What risk level is email_read_message? +

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

Can I rate-limit email_read_message? +

Yes. Add a rate_limit block to the email_read_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.

How do I block email_read_message completely? +

Set action: deny in the PolicyLayer policy for email_read_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.

What MCP server provides email_read_message? +

email_read_message is provided by the ScopeGate MCP server (https://mcp.scopegate.cloud/{api_key}). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on ScopeGate, and thousands of servers like it.

This server

All 385 ScopeGate tools →

Across the catalogue

claude_read_file on Claude Bridge → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →