Skip to content

Usage Examples

This is a quick reference of natural language prompts you can use with any AI assistant connected to GitLab MCP Server, grouped by domain. Type the prompt in plain English and the server translates it into the right GitLab API operation automatically — the tabs below show which meta-tool and action each prompt maps to, across project management, code review, CI/CD, releases, and search.

Prompt: “Show me my GitLab projects”

The server calls gitlab_project with action: list, returning project names, descriptions, and URLs.

Prompt: “Create a bug report in my-group/my-project titled ‘Login page returns 404 after password reset’ with labels bug and priority::high”

The server calls gitlab_issue with action: create, setting the title, description, labels, and project in a single operation.

Prompt: “List all labels in the frontend project and create a new label called ‘accessibility’ with color #0052CC”

The server first calls gitlab_label with action: list to show existing labels, then action: create to add the new one.

Prompt: “Show me the progress on the Sprint 14 milestone in my-project”

The server calls gitlab_milestone with action: get, returning completion percentage, open/closed issue counts, and due date.

Prompt: “List all members of the frontend project and their access levels”

The server calls gitlab_member with action: list, returning team members with their roles and permissions.

Dynamic mode is the default, so the prompts above don’t reach a named meta-tool directly. Instead the assistant first discovers the action and its schema with gitlab_find_action, then runs it with gitlab_execute_action using a canonical domain.action ID:

gitlab_find_action → query: "list open merge requests"
gitlab_execute_action → action: "merge_request.list", params: { project_id: "42", state: "opened" }

For analysis tasks, the same flow discovers canonical analyze.* actions before execution:

gitlab_find_action → query: "analyze failed pipeline"
gitlab_execute_action → action: "analyze.pipeline_failure", params: { project_id: "42", pipeline_id: 12345 }