AI agents call geo_lookup 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 is a diagnostic lookup tool that queries and returns geolocation and hosting metadata about IP addresses or domains. It retrieves information without creating, modifying, deleting, or executing any operations. The 'is_hosting flag' is still a data attribute returned by the query. No side effects or state changes occur.
From the tool's definition Tool performs geolocation and hosting information lookup (country, city, ISP, ASN, CDN detection). The description indicates data retrieval operations: 'country, city, ISP, ASN, CDN detection, is_hosting flag' are all informational reads with no modification…
Attacks that exploit this kind of access
Geolocation and hosting: country, city, ISP, ASN, CDN detection, is_hosting flag. 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 geo_lookup: 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.
geo_lookup 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 geo_lookup 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 geo_lookup. 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.
geo_lookup 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 →