Skills/PyPI/mcp-shell-server

mcp-shell-server@1.1.14

VERIFIED· not started

Publisher claims: "MCP Shell Server - Execute shell commands via MCP protocol" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher tumf · publishing for 703 daysInstalls 3,055Last detonated 5d ago
$claude mcp add mcp-shell-server -- uvx mcp-shell-server
WatchReport an issue

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: Verified 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
no credential variables read in the code
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 under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx mcp-shell-server

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 2026-11-09 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

MEDIUM
Process kill commandtests/test_audit_logging.py:26 · Process kill command — agent can terminate processesprocess.kill = MagicMock()Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/test_command_validator.py:314 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files["awk", 'BEGIN { getline value < "/etc/passwd" }'],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandtests/test_shell_executor.py:159 · Process kill command — agent can terminate processesmock_process.kill = AsyncMock()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_process_manager.py:37 · Process kill command — agent can terminate processesprocess.kill = MagicMock()Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_process_manager_macos.py:71 · Process kill command — agent can terminate processesprocess.kill() # Force killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_process_manager_additional.py:118 · Process kill command — agent can terminate processes# Execute with timeout should kill process and re-raise exceptionFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_shell_executor.py:183 · Process kill command — agent can terminate processesmock_process.kill = AsyncMock()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actiontests/test_shell_executor.py:793 · File type combined with upload action — agent may exfiltrate local data files["cat", "<", "input.txt", ">", "output.txt"]Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandtests/test_process_manager_additional.py:261 · Process kill command — agent can terminate processes# Verify os.kill was called to re-raise the signalFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_shell_executor.py:1232 · Python subprocess execution detectedprobe = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/conftest.py:39 · Process kill command — agent can terminate processesprocess.kill = AsyncMock()Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_shell_executor.py:125 · Python subprocess execution detectedsubprocess.run(["git", "init", "-q", str(source)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_shell_executor_more_coverage.py:75 · Process kill command — agent can terminate processesmock_process.kill = AsyncMock(side_effect=kill_side_effect)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_shell_executor_more_coverage.py:71 · Process kill command — agent can terminate processes# Mock kill to raise ProcessLookupError to cover line 294Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_shell_executor.py:58 · Python subprocess execution detectedsubprocess.run(["git", "init", "-q", str(tmp_path)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_process_manager_macos.py:31 · Python subprocess execution detectedps = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Authorization escalation language.serena/memories/session_checkpoint_2025_09_06.md:19 · Authorization escalation language · informational: not an instruction file- **Environment**: Ubuntu user (uid:1000, gid:1000) with sudo accessFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandtests/test_process_manager_additional.py:20 · Process kill command — agent can terminate processesprocess.kill = MagicMock()Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_shell_executor.py:1965 · Python subprocess execution detectedprobe = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_process_manager_macos.py:142 · Python subprocess execution detectedps = subprocess.run(["pgrep", "-g", str(process.pid)], capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_shell_executor.py:238 · Process kill command — agent can terminate processesmock_process.kill = AsyncMock()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_command_validator.py:307 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files["sed", "-e1r /etc/passwd", "input"],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Process kill commandtests/test_process_manager_additional.py:229 · Process kill command — agent can terminate processes# Mock os.kill to prevent actual signal sendingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiontests/test_shell_executor_redirections.py:73 · File type combined with upload action — agent may exfiltrate local data fileshandler.validate_redirection_syntax(["cat", "<", "input.txt", ">", "output.txt"])Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedtests/test_shell_executor.py:1390 · Python subprocess execution detectedsubprocess.run(argv, stdout=subprocess.DEVNULL, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈53 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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 mcp-shell-server@1.1.14 as of 5d ago. This is the package itself, not its dependencies.