AI agents use create_sellerhub_domain 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.
Creating a marketplace listing modifies data in the SellerHub system by adding a new listing record. This is a Write operation because it creates new data reversibly (the listing can be delisted/removed). It is not Destructive because the action is not irreversible, and not Financial because it does not commit the AI to a direct monetary transaction—it merely advertises a domain for potential sale.
From the tool's definition Tool description states 'List a domain for sale on the SellerHub marketplace' — this creates a new marketplace listing, which is a reversible data modification operation.
Attacks that exploit this kind of access
List a domain for sale on the SellerHub marketplace. 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_sellerhub_domain: 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_sellerhub_domain 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_sellerhub_domain 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_sellerhub_domain. 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_sellerhub_domain 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 →