Skills/npm/gitlab-mcp

gitlab-mcp@13.3.0

CAUTION· startup only

Publisher claims: "Advanced GitLab MCP server" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher structured-world · publishing for 424 daysInstalls 17,924Last detonated 4d ago
What would fix thisWatchDispute verdict

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: Caution 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
GITLAB_AUTH_COOKIE_PATHGITLAB_TOKENNODE_TLS_REJECT_UNAUTHORIZEDOAUTH_CLIENT_IDOAUTH_CLIENT_SECRETOAUTH_DEVICE_POLL_INTERVALOAUTH_DEVICE_TIMEOUTOAUTH_ENABLEDOAUTH_ISSUEROAUTH_REFRESH_TOKEN_TTLOAUTH_SCOPESOAUTH_SESSION_SECRETOAUTH_TOKEN_TTLUSE_ACCESS_TOKENSUSE_CI_TOKENSUSE_WEBHOOKSConfiguration, not credentials: DASHBOARD_ENABLED, DEFAULT_NULL, GITLAB_ALLOWED_PROJECT_IDS, GITLAB_ALLOWED_TOOLS_REGEX, GITLAB_API_BODY_TIMEOUT_MS, GITLAB_API_CONNECT_TIMEOUT_MS, GITLAB_API_HEADERS_TIMEOUT_MS, GITLAB_API_RETRY_BASE_DELAY_MS, GITLAB_API_RETRY_ENABLED, GITLAB_API_RETRY_MAX_ATTEMPTS, GITLAB_API_RETRY_MAX_DELAY_MS, GITLAB_API_URL, GITLAB_CA_CERT_PATH, GITLAB_CROSS_REFS, GITLAB_DEFAULT_NAMESPACE, GITLAB_DEFAULT_PROJECT, GITLAB_DENIED_ACTIONS, GITLAB_DENIED_TOOLS_REGEX, GITLAB_FAILURE_THRESHOLD, GITLAB_HEALTH_CHECK_INTERVAL_MS, GITLAB_HTTP_KEEPALIVE_TIMEOUT_MS, GITLAB_INIT_TIMEOUT_MS, GITLAB_INSTANCE_CACHE_MAX, GITLAB_INSTANCE_TTL_MS
Where it talks to
no vendor host named in the codeAlso sw.foundation — 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 sw.foundation as well as its own vendor. The guard injects GITLAB_AUTH_COOKIE_PATH, GITLAB_TOKEN, NODE_TLS_REJECT_UNAUTHORIZED, OAUTH_CLIENT_ID, OAUTH_CLIENT_SECRET, OAUTH_DEVICE_POLL_INTERVAL, OAUTH_DEVICE_TIMEOUT, OAUTH_ENABLED, OAUTH_ISSUER, OAUTH_REFRESH_TOKEN_TTL, OAUTH_SCOPES, OAUTH_SESSION_SECRET, OAUTH_TOKEN_TTL, USE_ACCESS_TOKENS, USE_CI_TOKENS, USE_WEBHOOKS only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y @structured-world/gitlab-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 2026-11-11 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: README links to an external installer; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 44 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
23sprocessdependency install exit 0
43sclaimedstartup only: exited (0) before answering · '/tmp/ks-detonate-3lDl2m/task/home/work/acme-api/.claude/skills/gitlab-mcp/dist/src/main.js' ] } Node.js v22.23.4
43sprocessscript backend runs setup only
43sprocessno install scripts to re-run

Static findings

HIGH
README links to an external installerREADME.md → https://github.com/structured-world/gitlab-mcp/releases/latest/download/gitlab-mcp-codex.ziphttps://github.com/structured-world/gitlab-mcp/releases/latest/download/gitlab-mcp-codex.zipFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathspackage.json:598 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"dev:stdio": "node --env-file=.env.test -r source-map-support/register -r ts-node/register --experimental-specifier-resolution=node --experimental-print-required-tla --watch src/main.ts stdio",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathspackage.json:599 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"dev:sse": "node --env-file=.env.test -r source-map-support/register -r ts-node/register --experimental-specifier-resolution=node --experimental-print-required-tla --watch src/main.ts sse",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiondist/src/cli/list-tools.js:1026 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(JSON.stringify(output, null, 2));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathspackage.json:625 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"list-tools:dev": "node --env-file=.env.test -r source-map-support/register -r ts-node/register --experimental-specifier-resolution=node src/cli/list-tools.ts",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiondist/src/cli/list-tools.js:860 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(JSON.stringify(output, null, 2));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/src/cli/list-tools.js:829 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(JSON.stringify(output, null, 2));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathspackage.json:600 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"dev": "node --env-file=.env.test -r source-map-support/register -r ts-node/register --experimental-specifier-resolution=node --experimental-print-required-tla --watch src/main.ts",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/src/handlers.js:696 · npx invocation of non-well-known package — may execute untrusted code"Run 'npx @structured-world/gitlab-mcp setup' for interactive configuration, " +Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/src/oauth/config.js:107 · npx invocation of non-well-known package — may execute untrusted code│ npx @structured-world/gitlab-mcp setup │Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiondist/src/cli/list-tools.js:916 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(JSON.stringify(output, null, 2));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/src/cli/list-tools.js:715 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(JSON.stringify(output, null, 2));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathspackage.json:615 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files… - Unit test coverage\\n yarn test:integration - Integration tests (needs .env.test)\\n yarn test:all - Full suite (unit + integration)\\n yarn tes…Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈46 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

No advisories in OSV for @structured-world/gitlab-mcp@13.3.0 as of 4d ago. This is the package itself, not its dependencies.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim structured-world: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. README links to an external installer≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim structured-worldPropose a patch to the maintainer