Is GitLab MCP server safe?
What GitLab MCP server does
This server calls the GitLab API so an MCP client can create or update files, push several files in one commit, create repositories, issues, branches and merge requests, fork projects and search repositories. The npm author field lists GitLab, PBC, and npm marks the package as no longer supported. It needs a GitLab personal access token (GITLAB_PERSONAL_ACCESS_TOKEN), plus GITLAB_API_URL for self-hosted instances. Before installing, choose token scopes deliberately: the README lists read_api for read-only use, and read_repository and write_repository for repository operations.
- Node.js network egress
- npm prepare hook
- MCP tool surface detected
What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.
GitLab MCP server is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: install time execution, mcp tools detected and network egress — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
@modelcontextprotocol/
Get notified when this component changes
Change alerts aren't live yet. Leave your email and we'll let you know when they launch. We use it only for this and delete it on request.
Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of GitLab MCP server's authors. Report a false positive.
Behavioral traits
How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.
Findings (3)
package.json has a 'prepare' script (runs on git/local installs and before publishing).
"prepare": "npm run build",
Why it matters: Usually a build step, but confirm it doesn't fetch or run remote code.
Fix: Usually a legitimate build step; confirm it only builds and does not fetch or execute remote code.
The component makes outbound network requests.
const response = await fetch(url + queryParams, {const response = await fetch(`${GITLAB_API_URL}/projects/${encodeURIComponent(projectId)}/repository/branches`, {const response = await fetch(url, {const response = await fetch(`${GITLAB_API_URL}/projects/${encodeURIComponent(projectId)}/issues`, {const response = await fetch(`${GITLAB_API_URL}/projects/${encodeURIComponent(projectId)}/merge_requests`, {const response = await fetch(url, {const response = await fetch(`${GITLAB_API_URL}/projects/${encodeURIComponent(projectId)}/repository/tree`, {const response = await fetch(`${GITLAB_API_URL}/projects/${encodeURIComponent(projectId)}/repository/commits`, {const response = await fetch(url.toString(), {const response = await fetch(`${GITLAB_API_URL}/projects`, {Why it matters: Usually legitimate, but confirm the destinations are expected and no sensitive data leaves.
Fix: Confirm the destination hosts are expected and that no sensitive data is sent off-host.
An MCP tool surface (manifest or tool definitions) was found.
const server = new Server({server.setRequestHandler(ListToolsRequestSchema, async () => {server.setRequestHandler(CallToolRequestSchema, async (request) => {const transport = new StdioServerTransport();
Why it matters: Just context — review which tools it offers and their permissions.
Fix: Review the declared MCP tools and their permissions.
How attackers abuse these capabilities
Interactive labs on the attack class behind the rules above. They show the technique, not anything found in GitLab MCP server.
Maintain GitLab MCP server?
The free Claude Code plugin scans each npm, PyPI or MCP package with this report's open-source engine before the install command runs. It runs on your machine and needs no account.
Check your own component
Run the same evidence-backed scan on any MCP server, agent skill, or package.
Scan your own componentHow we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →