Grades are a hygiene check, not a security guarantee.

MCP, MCP server

Mcp Fence

Mcp Fence, an MCP server listed in the PlugVet directory.

Compatibility: Not stated.

Grade D

Two or more Medium findings, or a High finding. Only try it in a sandbox.

Graded by PlugVetRubric v2

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

Rescanned at commit e1e9b622b9cd, unchanged since the check below.

PERMISSION_SHELL_UNDECLARED SECRETS_PATH_CREDENTIAL AGENT_IGNORE_INSTRUCTIONS

Why this grade

  • PERMISSION_SHELL_UNDECLARED Medium

    Runs shell commands that the manifest or description does not mention.

    src/mcp_fence/cli.py, line 451 shutil.rmtree(destination)

  • SECRETS_PATH_CREDENTIAL Medium

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

    README.md, line 159 `--traversal-target`. They never aim at `/etc/shadow` or `~/.ssh/`.

  • AGENT_IGNORE_INSTRUCTIONS Medium

    Text tells the agent to ignore earlier instructions.

    docs/rule_catalog.md, line 67 (`ignore previous instructions`, `do not tell the user`, `exfiltrate`,

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.

If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.

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. requests shell access. No manifest field names shell or command execution.

    PERMISSION_SHELL_UNDECLARED PERMISSION_DELETE_FILES

    src/mcp_fence/cli.py, line 451

    shutil.rmtree(destination)

    src/mcp_fence/examples/vulnerable_shell_server/server.py, line 47

    proc = subprocess.run(

    src/mcp_fence/examples/vulnerable_shell_server/server.py, line 72

    proc = subprocess.run(

    Show more

    src/mcp_fence/mcp/stdio_client.py, line 64

    self._proc: subprocess.Popen[bytes] | None = None

    src/mcp_fence/mcp/stdio_client.py, line 79

    def proc(self) -> subprocess.Popen[bytes]:

    src/mcp_fence/sandbox/docker.py, line 183

    return subprocess.run(

    src/mcp_fence/scanner/code_scan.py, line 138

    msg="os.system() invokes a shell.",

    src/mcp_fence/scanner/code_scan.py, line 148

    msg="os.popen() invokes a shell.",

  • Install and update

    Pass

    No install-time script found, and dependencies are pinned or absent.

  • Network

    Concern

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

    NETWORK_NO_FIXED_HOST

    src/mcp_fence/llm/local_judge.py, line 71

    r = httpx.post(

    src/mcp_fence/llm/local_judge.py, line 93

    r = httpx.post(

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_PATH_CREDENTIAL

    README.md, line 159

    `--traversal-target`. They never aim at `/etc/shadow` or `~/.ssh/`.

    SECURITY.md, line 40

    `~/.ssh/id_*`, or other real sensitive paths.

  • Agent instructions

    Serious

    instructions tell the agent to ignore earlier instructions.

    AGENT_IGNORE_INSTRUCTIONS

    docs/rule_catalog.md, line 67

    (`ignore previous instructions`, `do not tell the user`, `exfiltrate`,

    src/mcp_fence/examples/vulnerable_metadata_server/server.py, line 6

    instructs an LLM to ignore previous instructions and exfiltrate env

  • 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.

Get the full report on this tool, £49

Note

Hygiene check of commit e1e9b622b9cd. can delete files. requests shell access. No manifest field names shell or command execution. can reach a host that is not written as a fixed address. reads a credential or environment file. instructions tell the agent to ignore earlier instructions.

Date and source

Date checked:

View source

github.com

Commit graded: e1e9b622b9cd986e2e2480ce46016365c9ab382c

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