mark_chat_read · Bluebubbles MCP: Risk & Policy

WHAT IT DOES

What mark_chat_read does on Bluebubbles

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

WHY IT NEEDS A POLICY

Why mark_chat_read needs a policy

This tool modifies chat metadata (read status) and sends a notification (read receipt) to other participants, making it a Write operation rather than a simple Read. While reversible in nature (can be marked unread), it creates observable side effects and changes state.

From the tool's definition Tool description states 'Mark a chat as read (sends read receipt visible to the other person)' - this modifies the read status of a chat and triggers a visible state change (read receipt) that is transmitted to other participants.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_chat_read Rate-limited

mark_chat_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_chat_read": {
      "limits": [
        {
          "counter": "mark_chat_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 Bluebubbles, so you can run agents against it safely.

FAQ

Questions about mark_chat_read

What does the mark_chat_read tool do? +

Mark a chat as read (sends read receipt visible to the other person). It is categorised as a Write tool in the Bluebubbles 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_chat_read? +

Register the Bluebubbles MCP server in PolicyLayer and add a rule for mark_chat_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 Bluebubbles. Nothing to install.

What risk level is mark_chat_read? +

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

Can I rate-limit mark_chat_read? +

Yes. Add a rate_limit block to the mark_chat_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_chat_read completely? +

Set action: deny in the PolicyLayer policy for mark_chat_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_chat_read? +

mark_chat_read is provided by the Bluebubbles MCP server (metaember/bluebubbles-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.