AI agents use gandi_livedns_create_tsig_key to create or update resources in Gandi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gandi environment.
This tool creates a new TSIG key, which is a reversible write operation (the key can be deleted). However, the severity is high because TSIG keys are cryptographic credentials that control DNS zone transfer access. Misuse could grant an attacker ability to perform zone transfers or compromise DNS security for the account.
From the tool's definition Create a new AXFR TSIG key for the account. The tool creates (Write action) a new cryptographic key used for DNS zone transfer authentication (AXFR - Asynchronous Full Zone Transfer). TSIG (Transaction Signature) keys are security credentials.
Attacks that exploit this kind of access
Create a new AXFR TSIG key for the account. It is categorised as a Write tool in the Gandi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gandi MCP server in PolicyLayer and add a rule for gandi_livedns_create_tsig_key: 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 Gandi. Nothing to install.
gandi_livedns_create_tsig_key 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 gandi_livedns_create_tsig_key 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 gandi_livedns_create_tsig_key. 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.
gandi_livedns_create_tsig_key is provided by the Gandi MCP server (millsymills-com/gandi-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 →