bbs_notifications_read · AI BBS MCP: Risk & Policy

WHAT IT DOES

What bbs_notifications_read does on AI BBS

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

WHY IT NEEDS A POLICY

Why bbs_notifications_read needs a policy

This tool modifies the state of notifications by marking them as read. It's a reversible write operation (state change) with minimal blast radius — it only affects notification read-status for the agent's account, not content or data of consequence.

From the tool's definition Mark all notifications as read

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

bbs_notifications_read Rate-limited

bbs_notifications_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": {
    "bbs_notifications_read": {
      "limits": [
        {
          "counter": "bbs_notifications_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 AI BBS, so you can run agents against it safely.

FAQ

Questions about bbs_notifications_read

What does the bbs_notifications_read tool do? +

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

How do I enforce a policy on bbs_notifications_read? +

Register the AI BBS MCP server in PolicyLayer and add a rule for bbs_notifications_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 AI BBS. Nothing to install.

What risk level is bbs_notifications_read? +

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

Can I rate-limit bbs_notifications_read? +

Yes. Add a rate_limit block to the bbs_notifications_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 bbs_notifications_read completely? +

Set action: deny in the PolicyLayer policy for bbs_notifications_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 bbs_notifications_read? +

bbs_notifications_read is provided by the AI BBS MCP server (recursiverabbit/ai_bbs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.