ShipSafe Security Scanner — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to ShipSafe local code patterns and dependency vulnerability checks: Do local findings remain separate from uploaded AI analysis and clearly label scanner limitations?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Independent security review for AI-built applications and coding-agent repositories.

What we know

Ship Safe MCP lets coding agents run full/focused repository scans, secret scans, retrieve findings and release-readiness checklists.

Maintenance / activity evidence

@ship-safe/mcp 0.6.4 published 2026-09-28T20:44:24.013Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Read/analyze source repository and write local reports/findings where applicable. Writes: Create local security reports/findings.
Authentication not yet verified.
Sensitive access: Source code, Secrets discovered by scanner, Security findings

Scanner must itself be trusted with source/secrets; findings should be independently reviewed.

Full authority, access and evidence limits are available in Review context and Access & risk.

All limitations / Review context

Do local findings remain separate from uploaded AI analysis and clearly label scanner limitations?

The bounded review of the publisher's documented ShipSafe local code patterns and dependency vulnerability checks and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

Scanner must itself be trusted with source/secrets; findings should be independently reviewed.
Read/analyze source repository and write local reports/findings where applicable.
Repository content is scanned by Ship Safe; exact external processing depends on scanner configuration.
Reviewed write actions: Create local security reports/findings
Sensitive access: Source code, Secrets discovered by scanner, Security findings
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
exact data-processing boundary
auth/pricing
Security scanners can produce false positives/negatives.
Full scan may inspect broad source/repository content.
Exact remote/local processing boundary and any LLM use need per-version verification.

Original activity observations

@ship-safe/mcp 0.6.4 published 2026-09-28T20:44:24.013Z

Technical identity

npm/@ship-safe/mcp

Exact implementation source: https://www.npmjs.com/package/@ship-safe/mcp ↗
Reviewed resource type: Testing / Debugging
Repository identity: asamassekou10/ship-safe
Package identity: npm:@ship-safe/mcp

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 8, 2026

Package registry metadata ↗
@ship-safe/mcp
Recorded package identity, distribution or download evidence.
GitHub repository ↗
asamassekou10/ship-safe
Repository reference; implementation attribution is not established for every document.
Includes references whose attribution is not established.

Setup · Watchlist

Testing / Debugging setup

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Set up testing / debugging integration
Publisher instructions
Shipping diagnostics; extra login may be required for AI analysis.
claude mcp add shipsafe -- npx -y @ship-safe/mcp; free local scan does not require login. AI analysis requires `npx @ship-safe/cli login` or the `shipsafe_login` MCP flow.
publisher documented install or connect · Publisher instructions
npx -y @ship-safe/mcp
publisher documented step or launch · Publisher instructions
claude mcp add shipsafe -- npx -y @ship-safe/mcp
Configure / authenticate
MCP100 setup guide
Authenticate with `npx @ship-safe/cli login` first; stored token at ~/.shipsafe/token.json is shared with CLI. Avoid paid verification as a connection check.
Check connection
Suggested check
Use official `shipsafe_status` tool for login status, tier, and remaining AI analysis quota; do not start quota-consuming AI scan.
Remove / uninstall / revoke
MCP100 setup guide
Generic client guidance (not publisher-specific uninstall): unregister MCP entry in the chosen client. If installed globally, remove the npm package separately. Revoke provider access separately through account controls, where supported. This does not erase local data or revoke funds/credentials automatically.
Unregister the named MCP entry from the actual host separately from removing a global npm install; no claim that either revokes remote credentials.
MCP uses ~/.shipsafe/token.json when CLI auth is used. Deleting this local file is local logout only; server-side session revocation steps not independently documented.

Official Documentation & Sources

What it does

Ship Safe MCP lets coding agents run full/focused repository scans, secret scans, retrieve findings and release-readiness checklists.

Capability: Security & Testing
Resource type: Testing / Debugging
Industry: Cybersecurity
Best fit: Independent security review for AI-built applications and coding-agent repositories.

Representative uses

Run full multi-agent repo scan
Scan secrets/API keys
Analyze one file
Read saved findings
Check release-readiness security checklist

Limitations

Security scanners can produce false positives/negatives.
Full scan may inspect broad source/repository content.
Exact remote/local processing boundary and any LLM use need per-version verification.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Not documented in the reviewed sources
Permissions: Read/analyze source repository and write local reports/findings where applicable.
Data handling: Repository content is scanned by Ship Safe; exact external processing depends on scanner configuration.
Cost: unknown
Risk and cautions: Scanner must itself be trusted with source/secrets; findings should be independently reviewed.

Access scope and cautions

Write actions: Create local security reports/findings
Sensitive access: Source code Secrets discovered by scanner Security findings
Risk level: moderate

FAQ

Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Run full multi-agent repo scan; Scan secrets/API keys; Analyze one file; Read saved findings; Check release-readiness security checklist.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx ship-safe mcp. Recorded transport: stdio. Prerequisites: Node/npm; source repository. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: No exact auth requirement was established for local MCP use.

Can it modify data or perform write operations?

Documented write actions include: Create local security reports/findings. Recorded permission boundary: Read/analyze source repository and write local reports/findings where applicable.

What data-handling boundary should I consider?

Repository content is scanned by Ship Safe; exact external processing depends on scanner configuration. Recorded sensitive-access context: Source code; Secrets discovered by scanner; Security findings.

What limitations and risks should I check before use?

Scanner must itself be trusted with source/secrets; findings should be independently reviewed. Security scanners can produce false positives/negatives. Full scan may inspect broad source/repository content. Exact remote/local processing boundary and any LLM use need per-version verification. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.