read_emails

Read emails from an IMAP mailbox over TLS. Requires EMAIL_USER and EMAIL_PASS env vars. Defaults to Gmail IMAP (imap.gmail.com:993). For Gmail, enable IMAP in Settings and use an App Password. Returns emails with headers (from, to, subject, date) and plain text body. Use IMAP SEARCH syntax to fil...

SERVERNodebench SOURCEnodebench-mcp

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-homenshum-nodebench/read-emails.md

WHAT IT DOES

What read_emails does on Nodebench

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

RISK

Why read_emails is rated Low

This is a read-only tool that retrieves email data without side effects. Categorized as Read rather than lower severity because it accesses potentially sensitive personal communications and requires credentials (EMAIL_USER, EMAIL_PASS), creating a high blast radius if an AI agent misuses it to access emails without authorization or exfiltrates sensitive information.

From the tool's definition Tool explicitly stated to 'Read emails from an IMAP mailbox' with returned headers and body content. No modification, deletion, or execution capabilities described.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs read_emails safely

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

read_emails Allowed

read_emails 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": {
    "read_emails": {}
  }
}

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

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

FAQ

Questions about read_emails

What does the read_emails tool do? +

How do I enforce a policy on read_emails? +

Register the Nodebench MCP server in PolicyLayer and add a rule for read_emails: 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 Nodebench. Nothing to install.

What risk level is read_emails? +

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

Can I rate-limit read_emails? +

Yes. Add a rate_limit block to the read_emails 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 read_emails completely? +

Set action: deny in the PolicyLayer policy for read_emails. 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 read_emails? +

read_emails is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Nodebench, and thousands of servers like it.

This server

All 824 Nodebench 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 →