restart_watcher

THE RISK

High Risk

Why restart_watcher needs a policy

Restarting a watcher transitions its state from stopped to running, which causes the system to resume active monitoring and potentially trigger alerting logic. This is an Execute operation because it causes side effects dependent on the watcher's configuration—specifically, resumption of real-time stream monitoring and any associated alert handlers.

From the tool's definition The tool performs 'restart' of a watcher component, which is an operational action that triggers state changes in a running system.

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

POLICY

How to control restart_watcher

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

policy.json

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

restart_watcher 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.

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

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More LiveTap tools

Destructive delete_watcher Stop and remove a watcher. Destructive destroy_connection Destroy a connection — stops the source subscriber, cleans up the stream buffer. Write create_connection Create a data connection. MQTT: connects to a broker and subscribes to topics. WebSocket: Write create_watcher Create an expression-based watcher on a connection. The watcher evaluates structured condi Write update_watcher Update a watcher Read get_connection Get detailed status of a specific connection. Read get_watcher Get details of a specific watcher including conditions, status, match count, and config. Read get_watcher_logs Get evaluation logs from a watcher — shows MATCH, SUPPRESSED, FIELD_NOT_FOUND, and CHECKPO

All 13 LiveTap tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in LiveTap → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about restart_watcher

What does the restart_watcher tool do? +

Restart a stopped watcher. It is categorised as a Execute tool in the LiveTap MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on restart_watcher? +

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

What risk level is restart_watcher? +

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

Can I rate-limit restart_watcher? +

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

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

restart_watcher is provided by the LiveTap MCP server (livetap/livetap). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every LiveTap tool call.

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

CHECK YOUR STACK →