Grades are a hygiene check, not a security guarantee.

MCP, MCP server

ai.smithery/blockscout-mcp-server

Provide AI agents and automation tools with contextual access to blockchain data including balance…

Compatibility: Not stated.

Grade B

Minor issues only, no Medium or High. Worth a quick look at the findings below 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 095ef2c03f1a, unchanged since the check below.

PERMISSION_DELETE_FILES NETWORK_NO_FIXED_HOST SECRETS_PATH_DOTENV INSTALL_DOCUMENTED_INSTALLER SECRETS_ENV_READ

Why this grade

  • PERMISSION_DELETE_FILES Low

    Contains a call that can delete files.

    hatch_build.py, line 64 result = subprocess.run(

  • NETWORK_NO_FIXED_HOST Low

    Makes a network call whose host is not written as a fixed address.

    AGENTS.md, line 241 ├── TESTING.md # Testing instructions for HTTP mode with curl commands

  • SECRETS_PATH_DOTENV Low

    Mentions a .env file.

    AGENTS.md, line 127 │ │ ├── .env.example

  • INSTALL_DOCUMENTED_INSTALLER Note

    Documentation shows an installer that pipes a download into a shell.

    .devcontainer/devcontainer.json, line 10 "uv": "curl -LsSf https://astral.sh/uv/install.sh | sh && sudo `which uv` pip install --system -e \".[test,dev]\" || exit 0"

  • SECRETS_ENV_READ Note

    Reads an environment variable whose name contains KEY, SECRET, TOKEN, PASSWORD or CREDENTIAL.

    .agents/skills/sepolia-foundry-tx/scripts/deploy.sh, line 162 if [[ -z "${BLOCKSCOUT_PRO_API_KEY:-}" && -f "$repo_root/.env" ]]; then

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

    Concern

    can delete files.

    PERMISSION_DELETE_FILES

    hatch_build.py, line 64

    result = subprocess.run(

    hatch_build.py, line 85

    shutil.rmtree(staged_path)

    scripts/bake_skill_metadata.py, line 15

    result = subprocess.run(

    Show more

    scripts/run_integration_tests.py, line 95

    proc = subprocess.run(cmd, cwd=PROJECT_ROOT, capture_output=True, text=True)

    scripts/run_integration_tests.py, line 133

    proc = subprocess.Popen(

  • Install and update

    Note

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

    INSTALL_DOCUMENTED_INSTALLER

    .devcontainer/devcontainer.json, line 10

    "uv": "curl -LsSf https://astral.sh/uv/install.sh | sh && sudo `which uv` pip install --system -e \".[test,dev]\" || exit 0"

  • Network

    Concern

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

    NETWORK_NO_FIXED_HOST

    AGENTS.md, line 241

    ├── TESTING.md # Testing instructions for HTTP mode with curl commands

    .agents/skills/sepolia-foundry-tx/scripts/deploy.sh, line 224

    curl -s --request POST --url "$rpc_url" --header "$rpc_headers" --header 'Content-Type: application/json' \

    .agents/skills/sepolia-foundry-tx/scripts/deploy.sh, line 230

    curl -s --request POST --url "$rpc_url" --header "$rpc_headers" --header 'Content-Type: application/json' \

    Show more

    .agents/skills/sepolia-foundry-tx/scripts/deploy.sh, line 236

    curl -s --request POST --url "$rpc_url" --header "$rpc_headers" --header 'Content-Type: application/json' \

    .agents/skills/sepolia-foundry-tx/scripts/deploy.sh, line 303

    txs_json="$(curl -s --request GET \

    blockscout_mcp_server/tools/transaction/get_transaction_info.py, line 47

    # Two genuine awaited operations: the concurrent fetch (gather) and the

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    AGENTS.md, line 127

    │ │ ├── .env.example

    AGENTS.md, line 244

    └── .env.example # Example environment variables

    .agents/skills/sepolia-foundry-tx/scripts/deploy.sh, line 162

    if [[ -z "${BLOCKSCOUT_PRO_API_KEY:-}" && -f "$repo_root/.env" ]]; then

    Show more

    .agents/skills/plan-export/SKILL.md, line 212

    #### .env.example

    .agents/skills/sepolia-foundry-tx/scripts/deploy.sh, line 165

    source "$repo_root/.env"

    .agents/skills/sepolia-foundry-tx/scripts/deploy.sh, line 168

    [[ -n "${BLOCKSCOUT_PRO_API_KEY:-}" ]] || die 4 "BLOCKSCOUT_PRO_API_KEY is not set (checked environment and $repo_root/.env)"

    blockscout_mcp_server/config.py, line 7

    # Load environment variables from a local .env file (current working directory)

    blockscout_mcp_server/config.py, line 9

    model_config = SettingsConfigDict(env_prefix="BLOCKSCOUT_", env_file=".env", env_file_encoding="utf-8")

  • Agent instructions

    Pass

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

  • Obfuscation

    Pass

    No encoded or minified payload found.

  • 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 095ef2c03f1a. can delete files. 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.

Date and source

Date checked:

View source

github.com

Commit graded: 095ef2c03f1aa3325da0baa41c8bf29aa1bbb6e6

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