AI agents use create_srv_record 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 creates new DNS SRV records, which is a reversible data modification. SRV records can be deleted or modified if needed, so it does not constitute irreversible destruction. However, misconfiguration could disrupt service discovery and cause application failures, warranting medium severity. The tool does not execute code or move funds, so it remains in Write category rather than Execute or Financial.
From the tool's definition Tool name 'create_srv_record' and description states 'Create an SRV record' — this creates/modifies DNS records, which aligns with Write category (creates data reversibly).
Attacks that exploit this kind of access
Create an SRV record (service locator) for a domain. 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 create_srv_record: 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.
create_srv_record 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 create_srv_record 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 create_srv_record. 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.
create_srv_record 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 →