waha_mark_chat_unread

THE RISK

Medium Risk

Why waha_mark_chat_unread needs a policy

The tool modifies chat metadata (unread status) but the change is completely reversible (can be marked read again). This is a Write operation rather than Read (which retrieves data without side effects) or Execute (which triggers external code/operations). The severity is medium because misuse could disrupt user experience by marking important chats as unread, but causes no data loss and is easily correctable.

From the tool's definition Tool performs 'Mark a chat as unread' which modifies chat state by 'adds an unread indicator to the chat'. This is a reversible state change operation.

Documented attack patterns abuse exactly the kind of access waha_mark_chat_unread gives an agent:

POLICY

How to control waha_mark_chat_unread

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

policy.json

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

waha_mark_chat_unread 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.

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

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More WAHA MCP Server tools

Destructive waha_clear_chat_messages Clear all messages from a chat. WARNING: This is a destructive operation that cannot be un Destructive waha_delete_chat Delete a chat completely. WARNING: This is a destructive operation that cannot be undone. Destructive waha_delete_group_picture Remove group profile picture. Destructive waha_delete_message Delete a specific message from a chat. This is a destructive operation and cannot be undon Destructive waha_remove_group_participants Remove member(s) from a group. Requires admin privileges. Destructive waha_leave_group Leave a group. Execute waha_revoke_group_invite_code Revoke current invite link and generate a new one. Requires admin privileges. Write waha_demote_group_admin Remove admin privileges from participant(s). Requires admin privileges.

All 52 WAHA MCP Server tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about waha_mark_chat_unread

What does the waha_mark_chat_unread tool do? +

Mark a chat as unread. This adds an unread indicator to the chat. It is categorised as a Write tool in the WAHA MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on waha_mark_chat_unread? +

Register the WAHA MCP Server MCP server in PolicyLayer and add a rule for waha_mark_chat_unread: 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 WAHA MCP Server. Nothing to install.

What risk level is waha_mark_chat_unread? +

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

Can I rate-limit waha_mark_chat_unread? +

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

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

waha_mark_chat_unread is provided by the WAHA MCP Server MCP server (seejux/waha-whatsapp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every WAHA MCP Server tool call.

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

CHECK YOUR STACK →