An unofficial MCP server for interacting with the Spaceship.dev domain management API
Server has 8 tools with basic schemas and descriptions, but significant gaps limit production readiness. All tools have descriptions (10-50 chars, below the 50-200 char baseline for LLM optimization) and input schemas with type definitions. However, parameter descriptions are minimal or absent, output schemas are undocumented, and error handling lacks recovery guidance. No tool annotations (readOnlyHint/destructiveHint) despite clear risk distinctions (2 WRITE, 6 READ_ONLY). Tool names follow verb_noun convention but descriptions are too terse to guide LLM selection. Missing pagination on list tools and no documented output structure.
Check if a domain is available for registration
Get the status of an asynchronous operation
Get contact information
Get DNS records for a domain
Get information about a domain
Get a list of domains
Register a new domain
Descriptions are 10-50 characters, well below the 50-200 char baseline for LLM optimization. Terse descriptions like 'Get a list of domains' and 'Get information about a domain' do not explain WHEN to use each tool or what distinguishes them.
Output schemas are not documented. Tools return complex objects (Domain, DnsRecord, Contact) but LLMs cannot see the field structure. This forces agents to guess what fields are available and risks failed downstream tool calls.
No tool annotations despite clear risk distinctions. register_domain and update_dns_records are WRITE operations that modify state, but lack destructiveHint annotation. All READ_ONLY tools lack readOnlyHint. Agents cannot distinguish safe from unsafe operations.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 45 | 2026-07-28+ | v2 |
Update DNS records for a domain
get_domains accepts take/skip pagination but no output limit is documented. Without a stated cap (e.g. 'returns max 100 domains'), agents may request thousands of items, exhausting context windows.
Error handling in SpaceshipClient catches axios errors and wraps them in McpError, but error messages are generic ('Spaceship API error: ...') without recovery guidance. LLMs cannot determine if errors are retryable, user-fixable, or fatal.