Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/vish288/mcp-gitlabWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/vish288/mcp-gitlab/gemini-extension)<a href="https://agentmods.dev/plugins/vish288/mcp-gitlab/gemini-extension"><img src="https://agentmods.dev/badge/plugins/vish288/mcp-gitlab/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/vish288/mcp-gitlab/gemini-extension"><img src="https://agentmods.dev/badge/plugins/vish288/mcp-gitlab/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mcp-gitlab scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "mcp-gitlab",
"version": "0.20.2",
"description": "GitLab MCP server (MCP 2026-07-28): projects, MRs, pipelines, CI/CD, issues; writes or read-only",
"mcpServers": {
"mcp-gitlab": {
"command": "uvx",
"args": [
"mcp-gitlab"
]
}
},
"settings": [
{
"name": "GITLAB_TOKEN",
"description": "GitLab personal access token (token mode). Optional after `mcp-gitlab auth login`; also accepts GITLAB_PAT, GITLAB_PERSONAL_ACCESS_TOKEN, GITLAB_API_TOKEN",
"required": false,
"sensitive": true
},
{
"name": "GITLAB_URL",
"description": "GitLab instance URL (e.g. https://gitlab.com)",
"required": true,
"sensitive": false
},
{
"name": "GITLAB_READ_ONLY",
"description": "Alias for MCP_READ_ONLY. Any value other than false/0/no/off/empty locks the server read-only; --read-only can only raise the lock",
"required": false,
"sensitive": false
},
{
"name": "MCP_READ_ONLY",
"description": "Locks the server read-only: write tools and write-workflow prompts are not listed and nothing lifts the lock at runtime. Shared name across the mcp-* servers; set it in the deployer's env",
"required": false,
"sensitive": false
},
{
"name": "GITLAB_AUTH",
"description": "Authentication mode: token (default) or oauth (OAuth 2.1 proxy; streamable-http only)",
"required": false,
"sensitive": false
},
{
"name": "GITLAB_OAUTH_CLIENT_ID",
"description": "Application ID of the GitLab OAuth app (oauth mode, or local sign-in on a self-managed instance)",
"required": false,
"sensitive": false
},
{
"name": "GITLAB_OAUTH_CLIENT_SECRET",
"description": "Secret of the GitLab OAuth app (oauth mode)",
"required": false,
"sensitive": true
},
{
"name": "GITLAB_OAUTH_BASE_URL",
"description": "Public URL of this server, no trailing slashWhat ships with it
4 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed 8d20a810fcf6
- 2d ago Changed · +12 lines c92cae967909
- 3d ago Changed 175db330502c
- 4d ago Changed 0145f8728b8f
- 5d ago Changed 546f27068f55
- 9d ago Changed f245502d5842
- 10d ago Changed · +36 lines 3636cca79d31
- 12d ago Changed 7baaf77e8cb3
- 18d ago Changed · +6 lines 2ed5f3cfffe0
- 19d ago First seen · 28 lines scan A 7199f62d7731
mcp-gitlab is a plugin published in the GitHub repository vish288/mcp-gitlab (6 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-20.
Other plugins, from other repositories
forgedock
Autonomous AI development pipeline that uses GitHub as a structured knowledge graph for Claude Code agents. Adds /work-on, /review-pr, /quality-gate, /orchestrate, and 20+ pipeline commands.
pr-trains
Batch operators for GitHub queues: review-train reviews every open PR, fix-train applies requested changes, fix-ci-train turns red CI green, merge-train fixes and merges in dependency order, issue-train triages and builds one PR per actionable issue — all with parallel sub-agents and one grouped confirmation.
hunch
A git-native reasoning graph of decisions, bugs, and invariants for your codebase — queried and enforced at reasoning time. Adds the hunch MCP tools plus /hunch:capture, /hunch:heal, /hunch:why, /hunch:fix, /hunch:fragile.
workflow
Code review and worktree workflow commands.
ci-review
CI-optimized code review: multi-agent parallel review with confidence scoring and atomic GitHub PR review posting via gh api.
diffctx
Selects the minimum code an LLM needs to review a git diff.