Grades are a hygiene check, not a security guarantee.

MCP, MCP server

Mcp Security

Public repository google/mcp-security.

Compatibility: Not stated.

Grade C

One Medium finding. Read the findings before installing.

Graded by PlugVetRubric v2

Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.

Rescanned at commit 9cc13ca88795, unchanged since the check below.

SECRETS_PATH_CREDENTIAL

Why this grade

  • SECRETS_PATH_CREDENTIAL Medium

    Mentions a credential store path (~/.ssh, id_rsa, .npmrc, .aws/credentials, credentials.json, .netrc).

    run-with-google-adk/src/mcp_security_agent/config.py, line 36 """Finds local .gcloud/application_default_credentials.json if present."""

Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.

Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.

What was checked

Plain notes from the hygiene checks.

  • Permissions

    Note

    requests shell access. The manifest names this permission.

    PERMISSION_SHELL_DECLARED

    run-with-google-adk/src/mcp_security_agent/config.py, line 110

    res = subprocess.run(

  • Install and update

    Note

    The docs document an installer that pipes a download into a shell.

    INSTALL_DOCUMENTED_INSTALLER

    extensions/google-secops/skills/setup-gemini-cli/SKILL.md, line 18

    * If not, guide: `curl -LsSf https://astral.sh/uv/install.sh | sh`

  • Network

    Concern

    can reach a host that is not written as a fixed address.

    NETWORK_NO_FIXED_HOST

    run-with-google-adk/static/app.js, line 112

    const res = await fetch(`${API_BASE_URL}/app_name`);

    run-with-google-adk/static/app.js, line 128

    const res = await fetch(`${API_BASE_URL}/info`);

    run-with-google-adk/static/app.js, line 170

    const res = await fetch(url);

    Show more

    run-with-google-adk/static/app.js, line 339

    const response = await fetch(`${API_BASE_URL}/chat`, {

    docs/soar_integrations/qualys_vm.md, line 116

    * `lowest_severity_to_fetch` (List[str], optional): Minimum severity level to fetch (e.g., `["3"]`).

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_CREDENTIAL SECRETS_PATH_DOTENV

    run-with-google-adk/sample_servers_to_integrate/agents/demo_idp_agent.py, line 42

    csec = client_secret or os.getenv("IDP_CLIENT_SECRET", "demo-client-secret")

    run-with-google-adk/sample_servers_to_integrate/agents/demo_xdr_agent.py, line 42

    csec = client_secret or os.getenv("XDR_CLIENT_SECRET", "demo-client-secret")

    run-with-google-adk/src/mcp_security_agent/config.py, line 36

    """Finds local .gcloud/application_default_credentials.json if present."""

    Show more

    run-with-google-adk/src/mcp_security_agent/cli.py, line 94

    "CLI flags ([cyan]--secops[/cyan], [cyan]--scc[/cyan]), or [cyan].env[/cyan].\n"

    run-with-google-adk/src/mcp_security_agent/config.py, line 24

    str(_pkg_dir.parent / ".env"),

    run-with-google-adk/src/mcp_security_agent/config.py, line 25

    str(_pkg_dir / ".env"),

    run-with-google-adk/src/mcp_security_agent/config.py, line 26

    ".env",

    run-with-google-adk/src/mcp_security_agent/config.py, line 38

    Path.cwd() / ".gcloud" / "application_default_credentials.json",

    run-with-google-adk/src/mcp_security_agent/config.py, line 39

    _pkg_dir / ".gcloud" / "application_default_credentials.json",

    run-with-google-adk/src/mcp_security_agent/config.py, line 40

    _pkg_dir.parent / ".gcloud" / "application_default_credentials.json",

    run-with-google-adk/src/mcp_security_agent/config.py, line 72

    adc_path = os.getenv("GOOGLE_APPLICATION_CREDENTIALS") or _discover_local_adc()

    run-with-google-adk/src/mcp_security_agent/config.py, line 194

    if self.google_application_credentials and not os.environ.get("GOOGLE_APPLICATION_CREDENTIALS"):

    run-with-google-adk/src/mcp_security_agent/config.py, line 206

    if self.google_api_key and not os.environ.get("GOOGLE_API_KEY"):

    run-with-google-adk/src/mcp_security_agent/config.py, line 213

    if self.use_vertex_ai or (target_project and not self.google_api_key and not os.environ.get("GOOGLE_API_KEY")):

    server/gti/gti_mcp/server.py, line 35

    api_key = os.getenv("VT_APIKEY")

  • Agent instructions

    Pass

    No instruction to ignore earlier instructions or to hide a step.

  • Obfuscation

    Note

    the file cap was reached before every file was read.

    OBFUSCATION_FILE_CAP_REACHED

    server/gti/gti_mcp/tools/threat_profiles.py, line 1

    # Copyright 2025 Google LLC

  • Licence

    Pass

    A licence file is present (LICENSE).

  • Maintainer activity

    Pass

    The latest commit is within the last 365 days.

Note

Hygiene check of commit 9cc13ca88795. requests shell access. The manifest names this permission. The docs document an installer that pipes a download into a shell. can reach a host that is not written as a fixed address. reads a credential or environment file. the file cap was reached before every file was read.

Date and source

Date checked:

View source

github.com

Commit graded: 9cc13ca887953b4a9a5a33403c778d7de2d94196

This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.

Read how this letter is chosen