Connect GitLab MCP to your AI agents, securely.
One secured endpoint for every GitLab call your AI agents make, scoped per user, inspected, and logged.Try GitLab MCP now
What your agents can ask once GitLab MCP is connected.
“List my open merge requests in this project”
“Show the failed jobs in the latest pipeline”
“Create a work item for this bug”
“Read the file at app/models from the default branch”
“Which critical vulnerabilities are open?”
“Leave review comments on this merge request”
Select the tools your AI agents can call
46 tools from the GitLab MCP schema.
Showing 46 tools
What GitLab MCP exposes
GitLab MCP groups its 46 tools into 11 categories, each with a suggested starting policy.
| Category | Covers | Access | Suggested policy |
|---|---|---|---|
| Repository | Commits, branches, files, tree, releases and tags | Read / Write | Scope projects; audit commits and branch creation |
| Merge Requests | Merge request details, listing, creation, review and merge | Read / Write | Require approval for merges |
| CI/CD | Pipelines, jobs, logs and artifact files | Read / Write | Restrict pipeline execution |
| Duo | GitLab Duo agents, flows and agent sessions | Read / Write | Approve agent session execution |
| Work Items | Issues, tasks, epics, links and saved views | Read / Write | Audit changes |
| Projects | Project metadata, members and forking | Read / Write | Limit organization access |
| Security | Vulnerability listing, detail and state changes | Read / Write | Limit access to security findings |
| Search | Full-text search, label search and semantic code search | Read | Limit access to intended projects |
| Notes | Comments on merge requests and work items | Read / Write | Audit publishing |
| Users | User lookup by username or ID | Read | Limit organization access |
| Server | MCP server version | Read | Allow version checks |
Connect GitLab MCP to your AI agent
Four steps, under ten minutes.
- 01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
- 02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
- 03
Connect GitLab
Find GitLab in the tool list and connect it.
- 04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.
Permissions down to the single tool
You do not allow GitLab MCP or block it. You allow the exact tools each agent can call, one by one.
| GitLab MCP | 46 TOOLS AVAILABLE |
|---|---|
| Code review agent | 4 tools, read only |
| Issue triage bot | 9 tools |
| Platform team assistant | all 46 tools |
- Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
- Default denyA tool you have not enabled is never exposed to the agent.
- Approval on writesTools that change or delete things can require a human to confirm.
Is GitLab MCP secure?
One endpoint instead of raw credentials. Every call is checked against policy and logged.
| AI agentsConnect through your MCP client configuration. | NeuralTrustApply controls based on your configuration. | GitLab MCP46 documented tools. |
|---|---|---|
| Coding assistants | Connection & credentialsper user | Repository10 tools |
| Internal copilots | Tool access policiesdeny by default | Work Items6 tools |
| Workflow automations | Request & response inspectioninline | Merge Requests5 tools |
| Compatible MCP clients | Activity monitoringalerts and logs | All other tools25 tools |
Use GitLab MCP with any AI agent framework
Setup guides for the tools your team already uses.
- Claude CodeSetup guide
- CursorSetup guide
- CodexSetup guide
- WindsurfSetup guide
- Gemini CLISetup guide
- Google AntigravitySetup guide
- GitHub CopilotSetup guide
- Claude EnterpriseSetup guide
- Microsoft Copilot StudioSetup guide
- Open WebUISetup guide
- LangChainSetup guide
- HaystackSetup guide
- Strands AgentsSetup guide
- Vercel AI SDKSetup guide
- n8nSetup guide
Common questions about running GitLab MCP through TrustGate.
Other MCP servers
More servers from the catalog.
GitHub
Securely connect your AI agents to GitHub through TrustGate: repositories, issues, pull requests, Actions, and 92 more tools, scoped per agent and logged.
96 toolsViewAtlassian
Securely connect your AI agents to Atlassian through TrustGate: Jira, Confluence, Bitbucket, Jira Service Management and more, scoped per agent and logged.
248 toolsViewLinear
Securely connect your AI agents to Linear through TrustGate: issues, projects, cycles, documents and teams, scoped per agent and logged.
78 toolsView
Connect GitLab MCP instantly
Pick the tools, point your agent at TrustGate, and GitLab MCP is live: scoped, inspected, logged.