Skills/PyPI/proliant-mcp

proliant-mcp@0.16.0

CAUTION· not started

Publisher claims: "MCP server that turns AI agents into your assistant for managing HPE compute: ProLiant (iLO), Compute Ops Management (GreenLake) and Synergy / OneView" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher hjma29 · publishing for 4 daysInstalls 2,831Last detonated 28 min ago

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
HPECOM_CLIENT_SECRETILO_PASSWORDONEVIEW_PASSWORDConfiguration, not credentials: DISPLAY, HPECOM_CLIENT_ID, HPECOM_REGION, ILO_HOST, ILO_NAME, ILO_USERNAME, ILO_VERIFY_SSL, ONEVIEW_HOST, ONEVIEW_NAME, ONEVIEW_USERNAME, ONEVIEW_VERIFY_SSL, PROLIANT_MCP_CONFIG, PROLIANT_MCP_NO_BROWSER, USERNAME, WAYLAND_DISPLAY
Where it talks to
no vendor host named in the codeAlso hpe.com — 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 hpe.com as well as its own vendor. The guard injects HPECOM_CLIENT_SECRET, ILO_PASSWORD, ONEVIEW_PASSWORD only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx proliant-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 0.13.0

vet-skills diff proliant-mcp 0.13.0 0.16.0

In the sandbox, this version reached for nothing 0.13.0 did not. Compared from the two recorded runs, not from source.

0.13.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-22 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompting user to enter sensitive credentials; Prompting user to enter sensitive credentials. 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
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

CRITICAL
Prompting user to enter sensitive credentialssrc/proliant_mcp/chat.py:84 · Prompting user to enter sensitive credentials — social engineeringtitle: str = "Enter your password"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Python subprocess execution detectedsrc/proliant_mcp/chat.py:273 · Python subprocess execution detectedsubprocess.Popen(["xdg-open", url], **quiet)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/proliant_mcp/inventory_cache.py:57 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/proliant_mcp/chat.py:269 · Python subprocess execution detectedos.startfile(url) # type: ignore[attr-defined]Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/proliant_mcp/chat.py:271 · Python subprocess execution detectedsubprocess.Popen(["open", url], **quiet)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Prompting user to enter sensitive credentialssrc/proliant_mcp/chat_inventory.py:192 · Prompting user to enter sensitive credentials — social engineeringmessage=f"Type the password shared by the {len(missing)} entries that have none.",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Python subprocess execution detectedsrc/proliant_mcp/inventory.py:136 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈74 tok
1 file · 26 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

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  2. Unclaimed publisher≈ +8 on the totalClaim hjma29: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  4. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim hjma29Propose a patch to the maintainer