Skills/PyPI/nife-mcp-server

nife-mcp-server@1.0.4

VERIFIED· startup only

Publisher claims: "Model Context Protocol server for Nife.io GraphQL API" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher nifetency · publishing for 228 daysInstalls 68Last detonated 31 h ago
$claude mcp add nife-mcp-server -- uvx nife-mcp-server
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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
NIFE_ACCESS_TOKENConfiguration, not credentials: PYTHON
Where it talks to
no vendor host named in the codeAlso nife.io — 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
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, and read the third-party hosts first. The code names nife.io as well as its own vendor. The guard injects NIFE_ACCESS_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx nife-mcp-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 (3 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-13 and scored it 90/100 (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 · 20 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.0sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'
20sclaimedstartup only: exited (0) before answering · (node:975) [UNDICI-EHPA] Warning: EnvHttpProxyAgent is experimental, expect them to change at any time. (Use `node --trace-warnings ...` to show where the warning was created) /usr/bin/python3: Error while finding module specification for 'nife_mcp_server.intelligent_main' (ModuleNotFoundError: No module named 'nife_mcp_server')
20sprocessscript backend runs setup only
20sprocesssecond launch, clock +45 days, CI unset
20sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'

Static findings

LOW
False input termination markerSECURITY.md:148 · False input termination marker — attempts to end user input section · informational: not an instruction file-----END PGP PUBLIC KEY BLOCK-----Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandRELEASE_SUMMARY.sh:77 · File permission modification command — agent changes file ownership/permissionsecho " chmod +x bin/nife-mcp-server.js"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandmake_executable.sh:7 · File permission modification command — agent changes file ownership/permissionschmod +x update_claude_config.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification command.github/workflows/publish.yml:55 · File permission modification command — agent changes file ownership/permissionsrun: chmod +x bin/nife-mcp-server.jsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandmake_executable.sh:6 · File permission modification command — agent changes file ownership/permissionschmod +x run_server.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandrelease.sh:99 · File permission modification command — agent changes file ownership/permissionschmod +x bin/nife-mcp-server.jsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packageRELEASE_SUMMARY.sh:105 · npx invocation of non-well-known package — may execute untrusted codeecho " npx @nife/mcp-server"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandmake_executable.sh:4 · File permission modification command — agent changes file ownership/permissionschmod +x release.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandmake_executable.sh:8 · File permission modification command — agent changes file ownership/permissionschmod +x cleanup.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandmake_executable.sh:5 · File permission modification command — agent changes file ownership/permissionschmod +x RELEASE_SUMMARY.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈51 tok
1 file · 50 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 nife-mcp-server@1.0.4 as of 31 h ago. This is the package itself, not its dependencies.