mark_dialog_read · Kwork MCP: Risk & Policy

WHAT IT DOES

What mark_dialog_read does on Kwork

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

WHY IT NEEDS A POLICY

Why mark_dialog_read needs a policy

This tool updates message metadata (read/unread status) without deleting, destroying, or executing external code. It is a write operation that modifies data reversibly. The action is low-severity because marking messages as read has no destructive effects and causes minimal disruption if misused by an AI agent.

From the tool's definition Tool description: 'Пометить все сообщения в диалоге с пользователем как прочитанные' (Mark all messages in a dialog with a user as read). This modifies the read status of messages, which is a reversible state change.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_dialog_read Rate-limited

mark_dialog_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_dialog_read": {
      "limits": [
        {
          "counter": "mark_dialog_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 Kwork, so you can run agents against it safely.

FAQ

Questions about mark_dialog_read

What does the mark_dialog_read tool do? +

Пометить все сообщения в диалоге с пользователем как прочитанные. It is categorised as a Write tool in the Kwork 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_dialog_read? +

Register the Kwork MCP server in PolicyLayer and add a rule for mark_dialog_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 Kwork. Nothing to install.

What risk level is mark_dialog_read? +

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

Can I rate-limit mark_dialog_read? +

Yes. Add a rate_limit block to the mark_dialog_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_dialog_read completely? +

Set action: deny in the PolicyLayer policy for mark_dialog_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_dialog_read? +

mark_dialog_read is provided by the Kwork MCP server (simonether/kwork-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.