Skills/npm/mcp-graphql-enhanced

mcp-graphql-enhanced@4.18.0

VERIFIED

Publisher claims: "Enhanced MCP server for GraphQL with dynamic headers and robust variables parsing — a drop-in replacement for mcp-graphql." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher letoribo · publishing for 403 daysInstalls 277KLast detonated 29 min ago
$claude mcp add mcp-graphql-enhanced -- npx -y @letoribo/mcp-graphql-enhanced
WatchReport an issue

Coverage

Server started and answered tools/list.
Tested
MCP initialize and tools/list · every tool description, for hidden instructions · every file read, file written and host contacted by what ran
Not tested
what the tools do when called with real credentials

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 unpkg.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
what the tools do when called with real credentials

Connect it under the guard; read the third-party hosts first. The code names unpkg.com as well as its own vendor. The guard pins the network to the hosts the honeypot saw.

$vet-skills run --net declared -- npx -y @letoribo/mcp-graphql-enhanced

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

What changed since 4.17.2

vet-skills diff mcp-graphql-enhanced 4.17.2 4.18.0

In the sandbox, this version reached for nothing 4.17.2 did not. Compared from the two recorded runs, not from source.

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) on 2026-11-21 and scored it 88/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 28 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
8.2sprocessdependency install exit 0
28sclaimed2 tools: query-graphql, introspect-schema
28stools88bab553e254fbb3
28stools15f2c60417ba03e3
28sprocessscript backend runs setup only
28sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsdist/worker.js:60 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files...env.HEADERS,Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packagedist/helpers/deprecation.js:23 · npx invocation of non-well-known package — may execute untrusted codeconsole.error(" Instead of: npx mcp-graphql --endpoint http://example.com/graphql");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/helpers/deprecation.js:24 · npx invocation of non-well-known package — may execute untrusted codeconsole.error(" Use: ENDPOINT=http://example.com/graphql npx mcp-graphql");Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandpackage.json:35 · File permission modification command — agent changes file ownership/permissions"build": "tsc && chmod +x dist/index.js",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈73 tok
1 file · 29 in bundle
Tool list per prompt
≈626 tok
2 tools · 313 per tool
Handshake
502 ms
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 491

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.