AI agents call watchers.dns to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool monitors DNS activity and provides signed callbacks for host changes—a read-only observation mechanism. It retrieves state information about DNS records but does not create, modify, delete, or execute arbitrary operations. The 'signed callback' pattern suggests it returns verified information about observed events.
From the tool's definition Tool name 'watchers.dns' and description 'get a signed callback when a host' indicates a monitoring/notification mechanism that retrieves or observes DNS-related events without modifying data. The callback is informational rather than action-inducing.
Attacks that exploit this kind of access
WATCHER: get a signed callback when a host\. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for watchers.dns: 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. Nothing to install.
watchers.dns is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the watchers.dns 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 watchers.dns. 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.
watchers.dns is provided by the MCP server (@2sio/mcp). 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 →