Skills/PyPI/lantern-works-deals-mcp

lantern-works-deals-mcp@0.6.6

VERIFIED· not started

Publisher claims: "Read-only MCP server (stdio): GPU rental price comparison refreshed regularly, with each price's age shown (H100, H200, A100, L40S, RTX 4090/5090 and more) with price history, a stack cost optimizer, and AI-infra deals and free tiers." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher connormatthewdouglas · publishing for 26 daysInstalls 11,703Last detonated 28 min ago
$claude mcp add lantern-works-deals-mcp -- uvx lantern-works-deals-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
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso thelanternworks.com, workers.dev, creativecommons.org, datacrunch.io, ovhcloud.com, clore.ai, githubusercontent.com, runpod.io, thundercompute.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 under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx lantern-works-deals-mcp

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

What changed since 0.6.0

vet-skills diff lantern-works-deals-mcp 0.6.0 0.6.6

This version reaches for something 0.6.0 did not: 9 new hosts (clore.ai, creativecommons.org, datacrunch.io, githubusercontent.com, …). Compared from the two recorded runs, not from source.

New hosts
clore.ai, creativecommons.org, datacrunch.io, githubusercontent.com, ovhcloud.com, runpod.io, thelanternworks.com, thundercompute.com, workers.dev

0.6.0 was not run in the sandbox (static only); 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 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: 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
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedtests/test_badge_ref.py:8 · Python subprocess execution detectedout = subprocess.run(["node", "-"], input=js, capture_output=True, text=True, check=True).stdout.strip()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_gauge_b1_b2.py:54 · Python subprocess execution detectedp = subprocess.run([sys.executable, "scripts/import_scout_availability.py", str(snap)], cwd=ROOT, env=env,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
document.cookie accesstests/test_stack.py:105 · document.cookie access — can steal session cookiesassert "replaceState" not in html and "localStorage" not in html and "document.cookie" not in htmlFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python exec or eval of computed codetests/test_measurement.py:15 · Python exec or eval of computed codeexec(compile(ast.Module(body=keep, type_ignores=[]), "entry", "exec"), ns)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Unicode escape sequence detectedcore/gpu.py:258 · Unicode escape sequence detected — may contain obfuscated payloads_DASHES = re.compile("[\u2010\u2011\u2012\u2013\u2014\u2015\u2212]")Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
LOW
Dynamic module loadingtests/test_gpu_history.py:263 · Dynamic module loadingF = importlib.util.module_from_spec(spec); spec.loader.exec_module(F)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingtests/test_build_clore.py:15 · Dynamic module loadingbc = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actioncore/throughput.py:19 · File type combined with upload action — agent may exfiltrate local data files# source checkout. core/assets/gpu_throughput.json is a byte copy of data/gpu_throughput.json (tests enforce it).Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedtests/test_cost_pages.py:513 · Python subprocess execution detectedp = subprocess.run([sys.executable, str(ROOT / "scripts/import_scout_availability.py"), str(f)], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingtests/test_build_clore.py:16 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(bc)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_stack_page.py:40 · Python subprocess execution detectedres = json.loads(subprocess.run(["node", "-e", js], capture_output=True, text=True, check=True).stdout)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedmcp_server/server.py:60 · Python subprocess execution detectedout = subprocess.run(["git", "-C", str(Path(__file__).resolve().parent), "rev-parse", "HEAD"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingtests/test_two_reads.py:9 · Dynamic module loadingm = importlib.util.module_from_spec(spec); sys.modules["isa"] = m; spec.loader.exec_module(m)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈100 tok
1 file · 81 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.