WATCHER: get a signed callback when an indicator of compromise (IP or domain) changes malicious status across threat feeds. Arm once, pay once. Pass ioc (an IP address or domain). Fires when the malicious verdict flips; bounded by maxFires/expiry. The status at arm time is baselined. Signed (veri...
AI agents call watchers.ioc-reputation 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 is fundamentally a Read operation—it retrieves and monitors threat feed data to report on malicious status changes. While it involves setting up a watcher (which could seem Write-like), the core function is retrieving threat intelligence information rather than creating persistent state that modifies external systems.
From the tool's definition The tool 'get a signed callback when an indicator of compromise (IP or domain) changes malicious status' performs a query/monitoring operation that retrieves threat intelligence data.
Attacks that exploit this kind of access
WATCHER: get a signed callback when an indicator of compromise (IP or domain) changes malicious status across threat feeds. Arm once, pay once. Pass ioc (an IP address or domain). Fires when the malicious verdict flips; bounded by maxFires/expiry. The status at arm time is baselined. Signed (verify offline) + retried; recoverable via watchers.status. Returns a watcherId. 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.ioc-reputation: 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.ioc-reputation 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.ioc-reputation 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.ioc-reputation. 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.ioc-reputation 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 →