io.github.zereight/gitlab-mcp
GitLab MCP server for projects, merge requests, issues, pipelines, wiki, releases, and more.
Using io.github.zereight/gitlab-mcp in Claude, Cursor, Gemini CLI, Cline, or Zed?
MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).
Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less
uv tool install mcpindex-gate && mcpindex-config-wireSemantic screen found no manipulation pattern in the description. Conformance probe not yet run.
mcpindex.integrity.descriptionpassINFOevidence“No malicious instructions found”via static_description
- - Semantic screen only - the deterministic conformance probe has not run on this server
- - Confidence is reported but not yet calibrated (v1)
- - Screen reads the tool description, not the live behavior
- - advisory
- - registry description only no input schema
- - screen model 8b
Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.
Own this server? Screen its description →
That verdict was true at screening time (snapshot 2026-07-31).
Contracts can change after screening, with no version bump. The gate pins io.github.zereight/gitlab-mcp’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.
See your first HOLD in 2 minutes →
Related: how to trust an MCP server · screen before install · silent contract drift
A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.
[](https://mcpindex.ai/server/io-github-zereight-gitlab-mcp)<a href="https://mcpindex.ai/server/io-github-zereight-gitlab-mcp"><img src="https://mcpindex.ai/api/v1/badge/io-github-zereight-gitlab-mcp" alt="mcpindex verdict" height="20" /></a>GITLAB_PERSONAL_ACCESS_TOKENGitLab personal access token for local stdio use. Create a token with the GitLab scopes needed by the tools you plan to use, such as api or read_api.
GITLAB_JOB_TOKENOptional GitLab CI job token to use instead of a personal access token when running inside GitLab CI.
GITLAB_AUTH_COOKIE_PATHOptional path to a GitLab authentication cookie file for cookie-based authentication.
GITLAB_API_URLGitLab API base URL. Use https://gitlab.com/api/v4 for GitLab.com or your self-managed GitLab API URL.
GITLAB_ALLOWED_PROJECT_IDSOptional comma-separated list of GitLab project IDs that this server is allowed to access.
GITLAB_READ_ONLY_MODESet to true to expose only read-only tools and block write operations.
USE_GITLAB_WIKISet to true to enable GitLab wiki tools.
GITLAB_TOOLSETSOptional comma-separated list of toolsets to enable, such as projects, issues, merge_requests, pipelines, releases, users, groups, wiki, or search.
GITLAB_TOOLSOptional comma-separated list of individual tool names to add on top of enabled toolsets.
GITLAB_DENIED_TOOLS_REGEXOptional regular expression used to hide matching tools from the server.
GITLAB_TOOL_POLICY_APPROVEOptional comma-separated list of tool names that require explicit approval before execution.
GITLAB_TOOL_POLICY_HIDDENOptional comma-separated list of tool names to hide from tools/list.
NODE_TLS_REJECT_UNAUTHORIZEDSet to 0 only when you intentionally need to connect to a GitLab instance with invalid or self-signed TLS certificates.
GITLAB_CA_CERT_PATHOptional path to a custom CA certificate file for self-managed GitLab instances.
Free selector plus read-only GitHub bounty, agent harness, Actions, flake, and MCP drift decisions.
Read-only GitHub bounty, agent harness, Actions failure, flake, and MCP tool-drift decisions.
Scan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.