Skip to content

Usage Examples

These examples show natural language prompts you can use with any AI assistant connected to GitLab MCP Server. The server translates these into GitLab API operations automatically.

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: “Show me all open merge requests assigned to me”

The server calls gitlab_merge_request with action: list, filtering by assignee and state.

Prompt: “Analyze the code changes in merge request !42 for potential bugs and security issues”

The server uses gitlab_analyze_mr_changes (sampling), which fetches the diff, sends it to the LLM for analysis, and returns a structured review with findings.

Prompt: “Do a security review of MR !78 in the backend project”

The server uses gitlab_review_mr_security (sampling), which examines the diff for security vulnerabilities like injection flaws, hardcoded secrets, and authentication issues.

Prompt: “Summarize the review feedback on MR !42”

The server uses gitlab_summarize_mr_review (sampling), consolidating all review comments and discussions into a concise summary.


Prompt: “What’s the status of the latest pipeline in my-project?”

The server calls gitlab_pipeline with action: list, returning the most recent pipeline’s status, duration, and stages.

Prompt: “Why did pipeline #12345 fail?”

The server uses gitlab_analyze_pipeline_failure (sampling), which fetches job logs, identifies the failing step, and provides root cause analysis with suggested fixes.

Prompt: “Check the .gitlab-ci.yml in my-project for best practices”

The server uses gitlab_analyze_ci_configuration (sampling), analyzing the CI config for optimization opportunities, security issues, and best practice violations.


Prompt: “Create release v2.1.0 from tag v2.1.0 in my-project with release notes about the login fix and performance improvements”

The server calls gitlab_release with action: create, associating the release with the tag and setting the description.

Prompt: “Generate release notes for milestone ‘v2.1’ based on all closed issues and merged MRs”

The server uses gitlab_generate_release_notes (sampling), which collects all issues and merge requests in the milestone and generates categorized release notes (Features, Bug Fixes, Improvements).

Prompt: “Give me a progress report for the Q2 milestone”

The server uses gitlab_generate_milestone_report (sampling), providing metrics on completion percentage, velocity, blockers, and projected completion date.


Prompt: “Search for usages of the deprecated authenticateUser function across all my projects”

The server calls gitlab_search with action: code, searching across projects for the specified code pattern.

Prompt: “Identify technical debt in the backend project”

The server uses gitlab_find_technical_debt (sampling), analyzing issues, code patterns, and project metrics to identify areas of accumulated technical debt.

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.

Prompt: “Analyze the deployment history for the production environment over the last month”

The server uses gitlab_analyze_deployment_history (sampling), examining deployment frequency, success rates, rollback patterns, and DORA-like metrics.