shipcheck-mcp@0.24.0
CAUTION· not startedPublisher claims: "MCP verification server for AI coding agents — proves a feature works across UI, API, and database. Run with: uvx shipcheck-mcp" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
GITHUB_TOKENSHIPCHECK_API_TOKENSHIPCHECK_DATABASE_URLSHIPCHECK_GITHUB_APP_PRIVATE_KEYSHIPCHECK_GITHUB_TOKENConfiguration, not credentials: SHIPCHECK_GITHUB_APP_ID, SHIPCHECK_HOST, SHIPCHECK_MOUNT_PATH, SHIPCHECK_PORT, SHIPCHECK_TRANSPORT- Where it talks to
- no vendor host named in the code
- What the honeypot saw
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard. It asks for GITHUB_TOKEN, SHIPCHECK_API_TOKEN, SHIPCHECK_DATABASE_URL, SHIPCHECK_GITHUB_APP_PRIVATE_KEY, SHIPCHECK_GITHUB_TOKEN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-18 and scored it 60/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collects secret-named environment variables and sends data out; Access to sensitive file paths; Instructs the agent to modify its persistent memory or instruction files. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.lower = {k.lower(): v for k, v in os.environ.items() if v}Fix: Never read or enumerate credential locations; accept a documented environment variable instead.subprocess.run(Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.".env.example",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.4. After every meaningful change: update `.memory.md` + `.achievements.md` + `docs/` + run `shipcheck memory record`.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.- [x] **All install/MCP-add docs updated** to `claude mcp add shipcheck -- uvx shipcheck-mcp` across README, AGENTS.md, DEPLOYMENT.md, website docsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.7. After every meaningful change: update `.memory.md` + `.achievements.md` + `chat.md`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…rived live from `mcp.list_tools()` so it can't drift again. - **All install/MCP-add instructions updated** across `README.md`, `AGENTS.md`, `docs/DEPLOYMENT.md`, `website/pages/docs/{getting-started,mcp-server}.mdx`, …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.4. After every meaningful change: update `.memory.md` + `.achievements.md` + `chat.md`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Every meaningful change should update `.memory.md`.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.#### "Keep updating memory.md and chat.md — do not remove previous content, just append"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.7. After every meaningful change: update `.memory.md` + `.achievements.md` + run `shipcheck memory record`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
No advisories in OSV for shipcheck-mcp@0.24.0 as of 52 min ago. This is the package itself, not its dependencies.
What would make this Verified
20 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Collects secret-named environment variables and sends data out≈ +9 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
- Unclaimed publisher≈ +8 on the totalClaim shipcheck-contributors: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.