mark_inbox_read · Reddirect MCP: Risk & Policy

WHAT IT DOES

What mark_inbox_read does on Reddirect

AI agents use mark_inbox_read to create or update resources in Reddirect — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Reddirect environment.

WHY IT NEEDS A POLICY

Why mark_inbox_read needs a policy

This tool modifies inbox message metadata (read status) but does not delete, create new content, or execute arbitrary operations. The change is reversible—messages can be marked unread again. While it affects user account state, the blast radius is minimal and limited to message status flags. This is a straightforward Write operation.

From the tool's definition Tool name 'mark_inbox_read' and description 'Mark all unread inbox messages as read' indicates modification of message state. The action changes the read/unread status of inbox items, which is a reversible data modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_inbox_read Rate-limited

mark_inbox_read stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mark_inbox_read": {
      "limits": [
        {
          "counter": "mark_inbox_read_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about mark_inbox_read

What does the mark_inbox_read tool do? +

Mark all unread inbox messages as read. It is categorised as a Write tool in the Reddirect MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mark_inbox_read? +

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

What risk level is mark_inbox_read? +

mark_inbox_read is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit mark_inbox_read? +

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

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

mark_inbox_read is provided by the Reddirect MCP server (jeebus87/reddirect). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.