Skills/PyPI/mcp-gitlab

mcp-gitlab@0.22.0

VERIFIED· not started

Publisher claims: "GitLab MCP server for the MCP 2026-07-28 specification (MCP 2.0): projects, MRs, pipelines, CI/CD, approvals and issues for AI assistants. Runs with writes, or locked read-only via MCP_READ_ONLY" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher vish288 · publishing for 266 daysInstalls 19,493Last detonated 20 h ago
$claude mcp add mcp-gitlab -- uvx mcp-gitlab
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
GITLAB_API_TOKENGITLAB_AUTHGITLAB_HTTP_BEARER_TOKENGITLAB_OAUTH_BASE_URLGITLAB_OAUTH_CLIENT_IDGITLAB_OAUTH_CLIENT_SECRETGITLAB_OAUTH_JWT_KEYGITLAB_OAUTH_SCOPESGITLAB_PATGITLAB_PERSONAL_ACCESS_TOKENGITLAB_TOKEN or --gitlab-tokenConfiguration, not credentials: GITLAB_READ_ONLY, GITLAB_SSL_VERIFY, GITLAB_TIMEOUT, GITLAB_URL
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard. It asks for GITLAB_API_TOKEN, GITLAB_AUTH, GITLAB_HTTP_BEARER_TOKEN, GITLAB_OAUTH_BASE_URL, GITLAB_OAUTH_CLIENT_ID, GITLAB_OAUTH_CLIENT_SECRET, GITLAB_OAUTH_JWT_KEY, GITLAB_OAUTH_SCOPES, GITLAB_PAT, GITLAB_PERSONAL_ACCESS_TOKEN, GITLAB_TOKEN and talks to its vendor. 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 --net declared -- uvx mcp-gitlab

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; not started: dependency install failed; the server itself was not observed) on 2026-11-13 and scored it 87/100 (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
0.1sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
File permission modification commandDockerfile:31 · File permission modification command — agent changes file ownership/permissionsRUN useradd --create-home --uid 10001 app && chown -R app:app /appFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsAGENTS.md:26 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- **Entry point**: `src/mcp_gitlab/__init__.py` — click CLI, loads `.env` via python-dotenv, runs the FastMCP serverFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesCHANGELOG.md:315 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file- docs: add Documentation Freshness rule to AGENTS.md (#43) (e06baa2)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandsrc/mcp_gitlab/servers/gitlab.py:1278 · File permission modification command — agent changes file ownership/permissions"""Create a commit applying create/update/delete/move/chmod file actions in one call.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Access to sensitive file pathstests/unit/test_local_auth.py:437 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesleftovers = [p.name for p in store.path.parent.iterdir() if p.name.startswith(".credentials.")]Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Access to sensitive file pathstests/unit/test_prompts.py:91 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files_load_file(_PROMPTS_DIR, "../../../etc/passwd")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 pathssrc/mcp_gitlab/local_auth.py:191 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesdir=self.path.parent, prefix=".credentials.", delete=FalseFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
Instructs the agent to modify its persistent memory or instruction filesCHANGELOG.md:407 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file- docs: update AGENTS.md — add release workflow, fix stale info (9e6e4ea)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈5,413 tok
2 files · 70 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 mcp-gitlab@0.22.0 as of 7d ago. This is the package itself, not its dependencies.