AI agents call blacklist_check to retrieve information from Idig Dns without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and reports blacklist status information about IP addresses. It is purely diagnostic—querying external databases (Spamhaus, Barracuda, SpamCop, SORBS) for lookup results. There is no capability to modify, delete, execute code, or commit financial actions. The only risk is information disclosure (e.g., learning that an IP is blacklisted), which is low severity in a typical security context.
From the tool's definition Tool performs 'IP blacklist / DNSBL check' and 'Tests...against' known blacklist providers. These are query/lookup operations with no data modification, code execution, or side effects.
Attacks that exploit this kind of access
IP blacklist / DNSBL check. Tests A-record and MX IPs against Spamhaus, Barracuda, SpamCop, SORBS, and more. It is categorised as a Read tool in the Idig Dns MCP Server, which means it retrieves data without modifying state.
Register the Idig Dns MCP server in PolicyLayer and add a rule for blacklist_check: 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 Idig Dns. Nothing to install.
blacklist_check 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 blacklist_check 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 blacklist_check. 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.
blacklist_check is provided by the Idig Dns MCP server (https://mcp.softricks.net/sse). 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 →