mcp@0.12.4

VERIFIED· startup only

Publisher claims: "Agent-to-agent cloud service: deploys and runs your apps and services — domains, logs, real status." Observed in sandbox: calls api.nyxory.com only, touches nothing outside the project, writes no memory.

Registry npm (MCP server) · listed in the official MCP RegistryPublisher nyxory · publishing for 156 daysInstalls 0Last detonated 46 h ago
$claude mcp add mcp -- npx -y @nyxory/mcp
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

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
NYXORY_API_TOKENConfiguration, not credentials: NYXORY_API_URL, NYXORY_SOURCE
Where it talks to
nyxory.com (its own)
What the honeypot saw
no credential files read · reached only api.nyxory.com (its own)
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for NYXORY_API_TOKEN and talks to nyxory.com. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --secrets NYXORY_API_TOKEN=nyxory.com -- npx -y @nyxory/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; startup only; authenticated tool behavior not tested) on 2026-11-12 and scored it 85/100 (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: calls api.nyxory.com only, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 23 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
2.7sprocessdependency install exit 0
23sfilesystemread ~/.mcp-auth/mcp-remote-0.1.37/36a6c080913d2bbce5772f6a6a119ff8_client_info.json · ~/.mcp-auth/mcp-remote-0.1.37/36a6c080913d2bbce5772f6a6a119ff8_tokens.json · ~/.mcp-auth/mcp-remote-0.1.37/36a6c080913d2bbce5772f6a6a119ff8_lock.json outside project
23sfilesystemwrote ~/.mcp-auth/mcp-remote-0.1.37/36a6c080913d2bbce5772f6a6a119ff8_client_info.json · ~/.mcp-auth/mcp-remote-0.1.37/36a6c080913d2bbce5772f6a6a119ff8_code_verifier.txt · ~/.mcp-auth/mcp-remote-0.1.37/36a6c080913d2bbce5772f6a6a119ff8_lock.json
23snetworkCONNECT tcp://api.nyxory.com:443
23snetworkCONNECT tcp://api.nyxory.com:443
23sprocessexec /tmp/ks-detonate-WIxmPQ/task/home/work/acme-api/.claude/skills/mcp/node_modules/open/xdg-open
23sprocessexec /usr/bin/grep
23sprocessexec /usr/bin/uname
23sclaimedstartup only: exited (0) before answering · [2230] Initializing auth coordination on-demand [2230] OAuth callback server running at http://127.0.0.1:17325 [2230] Creating lockfile for server 36a6c080913d2bbce5772f6a6a119ff8 with process 2230 on port 17325 [2230] Authentication required. Waiting for authorization...
23sprocessscript backend runs setup only
23sprocessno install scripts to re-run

Static findings

MEDIUM
npx invocation of non-well-known packageserver/index.js:5 · npx invocation of non-well-known package — may execute untrusted code// @nyxory/mcp npm package (npx @nyxory/mcp) for stdio-only clients.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

No other findings across 189 lines in 5 files.

Cost to the agent

Instructions loaded
≈63 tok
1 file · 5 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 @nyxory/mcp@0.12.4 as of 46 h ago. This is the package itself, not its dependencies.