About Shipcheck MCP
Shipcheck MCP lets local MCP clients run read-only launch-risk scans on JavaScript and TypeScript repositories they are authorized to inspect. Its static analysis checks project files without executing code or making network requests.
Key features
- 01Scan JavaScript and TypeScript repositories
- 02Check launch risks across app and MCP server projects
- 03Output text, Markdown, JSON, or SARIF
- 04Read files without modifying or executing project code
Use cases
- 01Review a repository for launch risks before release
- 02Check an MCP server for documented execution and auth boundaries
- 03Generate a SARIF scan report
MCP support
Exposes the `scan_repository` tool to local MCP clients that support stdio servers. The tool scans authorized local repositories and returns results in a selected format.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
1Saved tool list · updated 3w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| root | string | No | Absolute or relative path to the authorized local repository. Defaults to the current working directory. |
| format | enum | No | Report rendering: text for terminals, markdown for review notes, json for automation, or sarif for code-scanning upload.text | markdown | json | sarif |
| failOn | enum | No | Pass/fail threshold. high fails only high findings; medium fails medium and high; low fails low through high; info fails on any finding.info | low | medium | high |
| strict | boolean | No | When true, enables extra release-readiness checks for launch handoff, directory submission, and production review. |
Details
From the project READMEshipcheck-mcp
MCP server that lets local MCP clients run Shipcheck on authorized JavaScript and TypeScript repositories.
Shipcheck scans apps and MCP servers for launch risks such as exposed private-looking env vars, unsigned Stripe webhooks, missing Supabase/Firebase rule evidence, debug routes, missing usage-cost guardrails, missing CI, loose dependencies, thin release docs, missing MCP smoke-test proof, undocumented STDIO execution boundaries, and undocumented remote MCP auth boundaries.
Tool page: https://tateprograms.com/shipcheck.html
Free MCP launch self-check: https://tateprograms.com/mcp-self-check.html
MCP directory launch checklist: https://tateprograms.com/mcp-directory-checklist.html
Paid MCP launch check: https://tateprograms.com/mcp-launch-review.html
Official MCP Registry: https://registry.modelcontextprotocol.io/v0/servers?search=shipcheck
Install
Run directly with npx:
npx --yes shipcheck-mcp
MCP Config
Add this server to an MCP client that supports stdio servers:
{
"mcpServers": {
"shipcheck": {
"command": "npx",
"args": ["--yes", "--package", "shipcheck-mcp", "shipcheck-mcp"]
}
}
}
STDIO MCP client config launches a local command. Review the command, args, and any env values before running generated configs, keep the package source trusted, and prefer pinned package versions when a deployment needs repeatability.
Tool
scan_repository
{
"root": ".",
"format": "markdown",
"failOn": "medium",
"strict": true
}
Formats: text, markdown, json, or sarif.
Severities: info, low, medium, or high.
Shipcheck is defensive static analysis, not a penetration test. It reads local project files, does not modify the repository, does not execute project code, and does not require network access. Run it only on repos you own or are authorized to inspect.
Development
npm install
npm run check
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.