Skills/PyPI/unblu-mcp

unblu-mcp@0.10.1

VERIFIED· not started

Publisher claims: "A model context protocol server for interacting with Unblu deployments." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher detailobsessed · publishing for 340 daysInstalls 161Last detonated 22 min ago
$claude mcp add unblu-mcp -- uvx unblu-mcp
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
UNBLU_API_KEYUNBLU_PASSWORDConfiguration, not credentials: UNBLU_BASE_URL, UNBLU_TRUSTED_HEADERS, UNBLU_USERNAME
Where it talks to
unblu.cloud (its own)Also python.org — 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 python.org as well as its own vendor. The guard injects UNBLU_API_KEY, UNBLU_PASSWORD only into requests to unblu.cloud (and its subdomains) and refuses the rest.

$vet-skills run --secrets UNBLU_API_KEY=unblu.cloud,UNBLU_PASSWORD=unblu.cloud -- uvx unblu-mcp

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 2026-11-20 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

HIGH
Auto-update or dynamic fetch configurationpyproject.toml:253 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeupdate-template = { shell = "copier update --trust . --skip-answered --defaults && uv sync --upgrade && prek autoupdate && echo ' ✓ Dependencies upgraded and hook versions updated'" }Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/unblu_mcp/_internal/providers_k8s.py:201 · Python subprocess execution detectedself._port_forward_process = subprocess.Popen( # noqa: S603Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
npx invocation of non-well-known packagepyproject.toml:236 · npx invocation of non-well-known package — may execute untrusted codeinspect = "DANGEROUSLY_OMIT_AUTH=true npx -y @modelcontextprotocol/inspector uv run unblu-mcp"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/unblu_mcp/_internal/providers_k8s.py:323 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/unblu_mcp/_internal/providers_k8s.py:167 · Python subprocess execution detectedauth_check = subprocess.run( # noqa: S603Fix: 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 · 17 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 unblu-mcp@0.10.1 as of 10 min ago. This is the package itself, not its dependencies.