vastai-mcp@0.1.3
CAUTION· not startedPublisher claims: "MCP server exposing Vast.ai GPU rental, volumes, and billing as tools" 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
VAST_API_KEYConfiguration, not credentials: _TYPER_STANDARD_TRACEBACK, MCP_FORCE_PORT, MCP_HOST, MCP_PORT, PYTHON_DOTENV_DISABLED, SPHINX_BUILD, TYPER_STANDARD_TRACEBACK, TYPER_USE_RICH- Where it talks to
- no vendor host named in the codeAlso python.org, rfc-editor.org, tiangolo.com, palletsprojects.com, httpbin.org, python-hyper.org, icom.museum, example.org, unicode.org, vast.ai — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- 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, and read the third-party hosts first. The code names python.org, rfc-editor.org, tiangolo.com, palletsprojects.com, httpbin.org, python-hyper.org, icom.museum, example.org, unicode.org, vast.ai as well as its own vendor. The guard injects VAST_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.
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 2026-11-20 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
The target .env file is created if it doesn't exist.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.path = os.path.join(cwd, ".env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.self.dotenv_path or ".env",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Get the value of a given key from the given .env.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Return a path for the ${pwd}/.env file.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.url = httpx.URL("HTTPS://jo%40email.com:a%20secret@müller.de:1234/pa%20th?search=ab#anchorlink")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.assert url == "https://jo%40email.com:a%[email protected]"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.help="Load environment variables from a .env file",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.https://jo%40email.com:a%20secret@müller.de:1234/pa%20th?search=ab#anchorlinkFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.# Load from .env file if specifiedFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Removes a given key from the given `.env` file.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose."""This script is used to set, get or unset values from a .env file."""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.help="Location of the .env file, defaults to .env file in current working directory.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Adds or Updates a key/value to the given .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.pty.spawn(sys.argv[1:], read)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."""Get the correct npx command for the current platform."""Fix: Pin versions and sources; vendor anything fetched at install time.spec.loader.exec_module(module) # type: ignoreFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(cmd, check=False, cwd=dirname)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.eval(bytecode, globs, locs)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.# Get the correct npx commandFix: Pin versions and sources; vendor anything fetched at install time.module = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.result = subprocess.run(cmd, check=False, cwd=dirname)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.os.execvpe(command[0], args=command, env=cmd_env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."npx not found. Please ensure Node.js and npm are properly installed "Fix: Pin versions and sources; vendor anything fetched at install time.logger.exception("Failed to load .env file")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.subprocess.run([cmd, "--version"], check=True, capture_output=True, shell=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.process = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."npx not found. Please ensure Node.js and npm are properly installed and added to your system PATH."Fix: Pin versions and sources; vendor anything fetched at install time.return "npx" # On Unix-like systems, just use npxFix: Pin versions and sources; vendor anything fetched at install time.logger.error("python-dotenv is not installed. Cannot load .env file.")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.p = Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.spec = importlib.util.find_spec(state.module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.module = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.return subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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
Not checked against OSV yet; the weekly check has not reached this version.
What would make this Verified
5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim pypi: 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.
- URL with embedded credentials≈ +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.
- npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
- Python exec or eval of computed code≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.