send_bark_notification · Bark MCP: Risk & Policy

WHAT IT DOES

What send_bark_notification does on Bark

AI agents invoke send_bark_notification to trigger actions in Bark. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why send_bark_notification needs a policy

This tool sends an external push notification to an iOS device via the Bark service. It doesn't merely read or write local data — it triggers an external operation whose effects (notification delivered to user's phone) depend on the arguments passed. Misuse could involve spamming a user with notifications or sending misleading alerts, hence medium severity.

From the tool's definition "Send a push notification via Bark to an iOS device" — triggers an external operation (push notification delivery) on a remote iOS device

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_bark_notification Rate-limited

send_bark_notification stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_bark_notification": {
      "limits": [
        {
          "counter": "send_bark_notification_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about send_bark_notification

What does the send_bark_notification tool do? +

Send a push notification via Bark to an iOS device. Use this to notify the user when: (1) Tasks are completed and need user attention, (2) Errors occur requiring user intervention, (3) User input or decisions are needed, (4) Testing or verification is required, (5) Long-running operations finish. Choose appropriate. It is categorised as a Execute tool in the Bark MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_bark_notification? +

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

What risk level is send_bark_notification? +

send_bark_notification is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit send_bark_notification? +

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

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

send_bark_notification is provided by the Bark MCP server (metrovoc/bark-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.