Resources & Prompts

Beyond tools, GitLab MCP Server exposes resources and prompts — two additional MCP primitives that provide context and reusable templates to AI assistants.

Resources

MCP resources provide read-only context data that clients can request at any time without invoking a tool. Resources are useful for providing background information that helps the LLM make better decisions.

The server exposes 46 resources across several categories:

Static resources (4)

Resource	Description
gitlab://user/current	Current authenticated user profile (username, email, state, admin status)
gitlab://groups	All GitLab groups accessible to the authenticated user
gitlab://workspace/roots	Workspace root directories from the MCP client, for project discovery via gitlab_resolve_project_from_remote
gitlab://schema/meta/	Catalog of registered meta-tools and their actions

Meta-schema resource template (1)

Resource	Description
gitlab://schema/meta/{tool}/{action}	JSON Schema for the params of a specific meta-tool action

Use the meta-schema resources when a client needs the exact parameter shape for a meta-tool action without expanding every schema in tools/list.

1. Read gitlab://schema/meta/ to get a JSON catalog with uri_template and a sorted list of registered meta-tools and actions.
2. Replace {tool} and {action} in gitlab://schema/meta/{tool}/{action} to read the JSON Schema for that action’s params object.
3. Call the meta-tool with the normal { "action": "...", "params": { ... } } envelope.

For example, gitlab://schema/meta/gitlab_merge_request/create returns the parameter schema for the create action of gitlab_merge_request. These schema resources are available regardless of META_PARAM_SCHEMA mode.

Project resource templates (23)

Resource	Description
gitlab://project/{project_id}	Project metadata (name, namespace, visibility, default branch)
gitlab://project/{project_id}/members	Project members with access levels (guest, reporter, developer, maintainer, owner)
gitlab://project/{project_id}/labels	Project labels with colors, descriptions, and issue/MR counts
gitlab://project/{project_id}/milestones	Project milestones with state, due dates, and web URLs
gitlab://project/{project_id}/branches	Branches with protection status, merge status, and default flag
gitlab://project/{project_id}/branch/{branch}	Single branch by name
gitlab://project/{project_id}/issues	Open issues with labels, assignees, author, and creation date
gitlab://project/{project_id}/releases	All releases with tag names, descriptions, and dates
gitlab://project/{project_id}/release/{tag_name}	Single release by tag
gitlab://project/{project_id}/tags	Repository tags with messages, commit SHAs, and protection status
gitlab://project/{project_id}/tag/{tag_name}	Single tag by name
gitlab://project/{project_id}/commit/{sha}	Single commit by SHA (stats, message, author)
gitlab://project/{project_id}/file/{ref}/{+path}	File contents at a ref (branch, tag, or SHA)
gitlab://project/{project_id}/wiki/{slug}	Wiki page by slug
gitlab://project/{project_id}/label/{label_id}	Single project label
gitlab://project/{project_id}/milestone/{milestone_iid}	Single project milestone
gitlab://project/{project_id}/board/{board_id}	Single issue board
gitlab://project/{project_id}/deployment/{deployment_id}	Single deployment
gitlab://project/{project_id}/environment/{environment_id}	Single environment
gitlab://project/{project_id}/job/{job_id}	Single CI/CD job
gitlab://project/{project_id}/feature_flag/{name}	Single feature flag
gitlab://project/{project_id}/deploy_key/{deploy_key_id}	Single deploy key
gitlab://project/{project_id}/snippet/{snippet_id}	Project-scoped snippet

Issue & merge request templates (4)

Resource	Description
gitlab://project/{project_id}/issue/{issue_iid}	Single issue details (title, state, labels, assignees, web URL)
gitlab://project/{project_id}/mr/{merge_request_iid}	Single merge request details (title, state, branches, author, merge status)
gitlab://project/{project_id}/mr/{merge_request_iid}/notes	Notes on a merge request
gitlab://project/{project_id}/mr/{merge_request_iid}/discussions	Discussion threads on a merge request

CI/CD resource templates (3)

Resource	Description
gitlab://project/{project_id}/pipelines/latest	Most recent pipeline (status, ref, SHA, source, web URL)
gitlab://project/{project_id}/pipeline/{pipeline_id}	Specific pipeline details by numeric ID
gitlab://project/{project_id}/pipeline/{pipeline_id}/jobs	All jobs for a pipeline (name, stage, status, duration, failure reason)

Group resource templates (5)

Resource	Description
gitlab://group/{group_id}	Group details (name, path, description, visibility)
gitlab://group/{group_id}/members	Group members with access levels, including inherited members
gitlab://group/{group_id}/projects	Projects within a group (ID, name, namespace, visibility)
gitlab://group/{group_id}/label/{label_id}	Single group label
gitlab://group/{group_id}/milestone/{milestone_iid}	Single group milestone

Personal snippet template (1)

Resource	Description
gitlab://snippet/{snippet_id}	Personal (user) snippet

Workflow guide resources (5)

Static best-practice guides for AI assistants — no API calls required.

Resource	Description
gitlab://guides/git-workflow	Git branching strategy, commit hygiene, and merge best practices
gitlab://guides/merge-request-hygiene	MR sizing, descriptions, review workflow, and merge strategies
gitlab://guides/conventional-commits	Conventional Commits specification with GitLab-specific examples
gitlab://guides/code-review	Structured code review checklist (quality, security, testing)
gitlab://guides/pipeline-troubleshooting	CI/CD debugging guide: common failures, job logs, retry strategies

Note

Resource URIs with {project_id}, {group_id}, etc. are resource templates. The client substitutes the actual ID or URL-encoded path when requesting the resource.

Accessing resources

MCP clients can request resources at any time using the resources/read method:

{
  "method": "resources/read",
  "params": {
    "uri": "gitlab://user/current"
  }
}

The server returns the resource content as structured JSON data.

To inspect meta-tool parameters, read the schema index first and then the action schema:

{
  "method": "resources/read",
  "params": {
    "uri": "gitlab://schema/meta/"
  }
}

{
  "method": "resources/read",
  "params": {
    "uri": "gitlab://schema/meta/gitlab_merge_request/create"
  }
}

Prompts

MCP prompts are reusable templates that guide AI assistants through common workflows. The server collects relevant data from GitLab and returns structured context that the LLM uses to produce high-quality outputs.

The server provides 38 prompt templates organized into categories:

Core prompts (12)

Merge request analysis, project overview, and personal productivity.

Prompt	Description
summarize_mr_changes	Summarize changed files and modifications in a merge request
review_mr	Structured code review with risk categorization and per-file metrics
suggest_mr_reviewers	Suggest reviewers based on changed files and active project members
mr_risk_assessment	Assess MR risk level (LOW/MEDIUM/HIGH/CRITICAL) based on size, files, and sensitive patterns
summarize_pipeline_status	Latest CI/CD pipeline status with failure reasons
summarize_open_mrs	All open MRs with age and merge status, highlighting stale MRs
project_health_check	Comprehensive health assessment (pipeline, MRs, branch hygiene)
generate_release_notes	Release notes from commits between two Git refs
compare_branches	Compare two branches showing commit differences and file changes
daily_standup	Daily standup summary from GitLab activity (done/planned/blockers)
team_member_workload	Workload summary for a team member over configurable time period
user_stats	User statistics with contribution events, MR/issue stats, and activity chart

Cross-project prompts (4)

Personal dashboards that aggregate across all accessible projects.

Prompt	Description
my_open_mrs	All open MRs where you are author or assignee
my_pending_reviews	All open MRs assigned to you as reviewer
my_issues	All issues assigned to you with overdue detection
my_activity_summary	Personal activity summary across projects for N days

Team prompts (4)

Group-level team management prompts.

Prompt	Description
user_activity_report	Detailed activity report for a specific user (for managers)
team_overview	Team dashboard with open MR counts and workload pie chart
team_mr_dashboard	All MRs for a group with state and target branch filters
reviewer_workload	Review distribution analysis to identify workload imbalances

Project report prompts (5)

Project-level analysis and reporting.

Prompt	Description
branch_mr_summary	All MRs targeting a branch with readiness summary
project_activity_report	Project activity report with events, merged MRs, and open issues
mr_review_status	Discussion health of open MRs (unresolved thread counts)
unassigned_items	Find open MRs and issues without assignees
stale_items_report	MRs and issues not updated for N days (default: 14)

Analytics prompts (4)

Velocity and release analytics.

Prompt	Description
merge_velocity	MR throughput, average time-to-merge, and daily chart
release_readiness	Release branch readiness (open MRs, conflicts, drafts)
release_cadence	Release frequency analysis with cadence chart
weekly_team_recap	Comprehensive weekly recap combining MRs, issues, events

Milestone & label prompts (4)

Milestone tracking and label analysis.

Prompt	Description
milestone_progress	Milestone progress with completion percentage and due date risk
label_distribution	Label usage distribution (open/closed issues, open MRs per label)
group_milestone_progress	Milestone progress across all projects in a group
project_contributors	Rank contributors by commits, additions, and deletions

Audit prompts (5)

Project configuration audit prompts.

Prompt	Description
audit_project_settings	Audit visibility, merge strategy, CI/CD, push rules, feature toggles
audit_branch_protection	Audit protected branches, access levels, code owner approvals
audit_project_access	Audit user access, blocked accounts, elevated privileges
audit_project_workflow	Audit labels, milestones, issue/MR templates
audit_project_full	Comprehensive audit combining all categories with a scorecard

Using prompts

Prompts are requested via the prompts/get MCP method:

{
  "method": "prompts/get",
  "params": {
    "name": "review_mr",
    "arguments": {
      "project_id": "my-group/my-project",
      "merge_request_iid": "42"
    }
  }
}

The server returns a structured prompt with context-aware content that the LLM uses to guide its workflow.

Configuration

Variable	Default	Description
CAPABILITY_SURFACE	full	full registers resources and prompts across tool surfaces; minimal keeps only workspace roots

Tip

Resources are particularly useful for providing project context at the start of a conversation. By reading the project resource, the LLM gains immediate understanding of the repository’s purpose, team, and current state.