watch_token · Rug Munch Intelligence MCP: Risk & Policy

WHAT IT DOES

What watch_token does on Rug Munch Intelligence

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

WHY IT NEEDS A POLICY

Why watch_token needs a policy

This tool creates a new monitoring configuration and registers a webhook endpoint — a reversible write operation. It does not read existing data passively, nor does it execute trades or delete anything. The blast radius is medium: a misused agent could register many unwanted webhooks or monitor tokens the user didn't intend, but no financial or destructive consequences follow directly from this action alone.

From the tool's definition "Set up real-time token monitoring with webhook alerts"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

watch_token Rate-limited

watch_token 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": {
    "watch_token": {
      "limits": [
        {
          "counter": "watch_token_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 Rug Munch Intelligence, so you can run agents against it safely.

FAQ

Questions about watch_token

What does the watch_token tool do? +

Set up real-time token monitoring with webhook alerts. It is categorised as a Write tool in the Rug Munch Intelligence MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on watch_token? +

Register the Rug Munch Intelligence MCP server in PolicyLayer and add a rule for watch_token: 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 Rug Munch Intelligence. Nothing to install.

What risk level is watch_token? +

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

Can I rate-limit watch_token? +

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

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

watch_token is provided by the Rug Munch Intelligence MCP server (marcus-rug-intel/rug-munch-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.