Skills/PyPI/openmcp-sdk

openmcp-sdk@0.2.20

VERIFIED· not started

Publisher claims: "Deploy MCP servers in seconds" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher pypi · publishing for 723 daysInstalls 60Last detonated 16 h ago
$claude mcp add openmcp-sdk -- uvx openmcp-sdk
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
CONCIERGE_AUTH_TOKENConfiguration, not credentials: CONCIERGE_API_URL, CONCIERGE_PROJECT_ID, OPENMCP_API
Where it talks to
no vendor host named in the codeAlso oaistatic.com, getconcierge.app — not the publisher's domain; check what for before connecting.
What the honeypot saw
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 oaistatic.com, getconcierge.app as well as its own vendor. The guard injects CONCIERGE_AUTH_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx openmcp-sdk

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 2026-11-13 and scored it 91/100 (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
Python subprocess execution detected__init__.py:153 · 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 detected__init__.py:163 · 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
npx invocation of non-well-known packagetemplates/chatgpt/assets/build.mjs:32 · npx invocation of non-well-known package — may execute untrusted codeexecSync(`npx vite build`, {Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈44 tok
1 file · 52 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 openmcp-sdk@0.2.20 as of 16 h ago. This is the package itself, not its dependencies.