mcp-shipcheck
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| shipcheck.auditA | Audit a local Node/TypeScript package for npm publish readiness (read-only). |
| shipcheck.packPreviewA | Show which files would be included by |
| shipcheck.explainFailureA | Explain a shipcheck failure code and suggest fixes (read-only). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose with no overlap: audit checks npm publish readiness, explainFailure decodes error codes, and packPreview shows file inclusions. An agent can easily distinguish between these three focused functions.
All tools follow a perfect verb_noun pattern (audit, explainFailure, packPreview) with consistent dot notation (shipcheck.*) and snake_case for multi-word names. The naming is highly predictable and readable throughout.
With 3 tools, this server is well-scoped for its purpose of npm package readiness checks. Each tool earns its place by covering distinct aspects (auditing, error explanation, and packing preview) without being overly sparse or bloated.
The toolset covers core npm package readiness workflows effectively: audit for checks, explainFailure for troubleshooting, and packPreview for validation. A minor gap exists in lacking a tool to directly fix issues (e.g., auto-correct or apply fixes), but agents can work around this using the explanations provided.