AI agents use save_dns_records to create or update resources in Spaceship — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Spaceship environment.
This tool modifies DNS records, which is a Write operation (data is created or updated reversibly). It is not Destructive because upsert operations can theoretically be undone by resetting records. Severity is high because misconfigured DNS can disrupt domain functionality, email delivery, and service availability, though the effects are technically reversible.
From the tool's definition Tool description states 'Save (upsert) DNS records for a domain using PUT with force overwrite.' The terms 'upsert' (update/insert) and 'PUT' indicate modification of existing data.
Attacks that exploit this kind of access
Save (upsert) DNS records for a domain using PUT with force overwrite. It is categorised as a Write tool in the Spaceship MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Spaceship MCP server in PolicyLayer and add a rule for save_dns_records: 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 Spaceship. Nothing to install.
save_dns_records 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 save_dns_records 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 save_dns_records. 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.
save_dns_records is provided by the Spaceship MCP server (naveenkm007/spaceship-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 →