AI agents use update_watcher to create or update resources in LiveTap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LiveTap environment.
This tool creates or modifies data in a reversible manner (Write category). It allows reconfiguration of monitoring rules but does not delete watchers (which would be Destructive), execute arbitrary code (Execute), or move money (Financial).
From the tool's definition Tool name 'update_watcher' and description 'Update a watcher' indicate modification of existing watcher configuration.
Documented attack patterns abuse exactly the kind of access update_watcher gives an agent:
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 update_watcher:
{
"version": "1",
"default": "deny",
"tools": {
"update_watcher": {
"limits": [
{
"counter": "update_watcher_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_watcher 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.
Free to start. No card required.
Update a watcher. It is categorised as a Write tool in the LiveTap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LiveTap MCP server in PolicyLayer and add a rule for update_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.
update_watcher is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_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.
Set action: deny in the PolicyLayer policy for update_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.
update_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.
Start from LiveTap, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 LiveTap tools catalogued and risk-classified — across an index of 43,000+ MCP servers.