mail.flagged

THE RISK

Low Risk

Why mail.flagged needs a policy

This tool retrieves and lists already-flagged email messages without creating, modifying, deleting, or executing any actions. It is a pure data retrieval operation similar to sibling tools like calendar.list_events and contacts.search on the same server. The blast radius of misuse is low—it can expose email metadata but cannot alter or destroy mailbox contents or trigger external operations.

From the tool's definition Tool name 'mail.flagged' and description 'List flagged (starred) email messages' indicates retrieval of existing data. Returns 'message headers' only, confirming read-only query operation with no modification or deletion of data.

Documented attack patterns abuse exactly the kind of access mail.flagged gives an agent:

POLICY

How to control mail.flagged

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mail.flagged": {}
  }
}

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

Create a free account and register Orchard — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Orchard tools

Destructive files.trash Move a file or folder to the Trash (reversible delete). Path must be under home directory. Destructive keynote.remove_slide Delete a slide from a Keynote presentation. Destructive numbers.remove_sheet Remove a sheet from a Numbers spreadsheet. Destructive reminders.delete_reminder Delete a reminder. Destructive files.move Move or rename files and folders. Supports batch operations for mass renaming. All paths m Destructive reminders.delete_list Delete a reminder list. Fails if the list has reminders unless force is true. Execute keynote.export Export a Keynote presentation to PDF, PowerPoint, PNG, or JPEG. Write files.copy Copy a file or folder to a new location. Both paths must be under home directory.

All 65 Orchard tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about mail.flagged

What does the mail.flagged tool do? +

List flagged (starred) email messages across all accounts. Returns message headers. Requires Mail.app to be running. It is categorised as a Read tool in the Orchard MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on mail.flagged? +

Register the Orchard MCP server in PolicyLayer and add a rule for mail.flagged: 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 Orchard. Nothing to install.

What risk level is mail.flagged? +

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

Can I rate-limit mail.flagged? +

Yes. Add a rate_limit block to the mail.flagged 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 mail.flagged completely? +

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

mail.flagged is provided by the Orchard MCP server (l22-io/orchard-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Orchard tool call.

Start from Orchard, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →