Create a new watch to monitor a URL for changes.
AI agents use create_watch to create or update resources in Mcp Watched — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Watched environment.
This tool creates and persists data (a new watch configuration). It is reversible via delete_watch (a sibling tool), so it is Write rather than Destructive. The severity is medium because while creating watches is low-risk on its own, an agent could create numerous watches to consume resources or monitor sensitive/private URLs if given unconstrained URL parameters.
From the tool's definition The tool description states it will 'Create a new watch to monitor a URL for changes' — this is a create operation that adds a new persistent entity (a watch) to the system.
Attacks that exploit this kind of access
Create a new watch to monitor a URL for changes. It is categorised as a Write tool in the Mcp Watched MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Watched MCP server in PolicyLayer and add a rule for create_watch: 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 Mcp Watched. Nothing to install.
create_watch 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 create_watch 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 create_watch. 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.
create_watch is provided by the Mcp Watched MCP server (ng-pr0ject/mcp-watched). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →