Resources & Prompts

Developer Documentation

This page is the user-facing overview. For the full reference, see docs/reference/resources and docs/reference/prompts.

Beyond tools, GitLab MCP Server exposes resources and prompts — two additional MCP primitives that provide context and reusable templates to AI assistants. Tools perform actions; resources supply read-only context on demand; prompts package a data-gathering workflow into a single reusable template.

What are MCP resources?

MCP resources provide read-only context data that clients can request at any time without invoking a tool. Resources are useful for supplying background information — a project’s metadata, members, labels, or latest pipeline — that helps the LLM make better decisions before it acts.

The server exposes 45 resources across several categories:

Note

MCP lists fixed resources and URI templates separately. In full mode, clients that only inspect resources/list see 8 fixed URIs: current user, groups, the tool manifest, and 5 workflow guides. The remaining 37 entries are URI templates returned by resources/templates/list and are read by substituting project, group, issue, MR, or other IDs at runtime.

Static resources (3)

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://tools	Surface-aware manifest of visible tools and executable entries

Tool manifest resource template (1)

Resource	Description
gitlab://tools/{id}	Accepted call shape and input schema for one entry from gitlab://tools

Use the tool manifest resources when a client needs the exact parameter shape for a meta-tool action without expanding every schema in tools/list, or when it wants to enumerate dynamic and individual entries in a consistent format.

1. Read gitlab://tools to get the active surface, visible tools, and executable entries.
2. Replace {id} in gitlab://tools/{id} to read the JSON Schema and call shape for that entry.
3. Call the meta-tool with the normal { "action": "...", "params": { ... } } envelope.

For example, gitlab://tools/gitlab_merge_request.create returns the parameter schema and call shape for the create action of gitlab_merge_request. These manifest resources are available with CAPABILITY_SURFACE=full or minimal, regardless of META_PARAM_SCHEMA mode. Dynamic clients can also use gitlab_find_action for ranked discovery and inline schemas.

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.

How do I read a resource?

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 accepted call shapes, read the surface-aware tool manifest first and then the action schema:

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

{
  "method": "resources/read",
  "params": {
    "uri": "gitlab://tools/gitlab_merge_request.create"
  }
}

What are MCP prompts?

MCP prompts are reusable templates that guide AI assistants through common workflows. When a client requests a prompt, the server collects the relevant data from GitLab and returns structured context that the LLM uses to produce a high-quality output — a code review, a release-notes draft, or a team report — without the user re-explaining the task each time.

The server provides 37 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
group_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_discussion_health	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

Git workflow prompts (2)

Commit history and MR authoring quality.

Prompt	Description
audit_commit_hygiene	Commit message and history quality between two Git refs
mr_description_quality	MR description readiness: context, linked work, tests, and risk notes

Audit prompts (2)

Project configuration audit prompts.

Prompt	Description
audit_project_workflow	Audit labels, milestones, issue/MR templates
audit_project_full	Comprehensive audit combining all categories with a scorecard

How do I use a prompt?

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, workflow guides, prompts, and gitlab://tools; minimal keeps gitlab://tools

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.

Frequently asked questions

What is the difference between resources, prompts, and tools?

GitLab MCP Server exposes three MCP primitives. Tools perform actions, such as creating an issue or merging a request. Resources provide read-only context data — a project’s metadata or members, for example — that a client can request at any time without invoking a tool. Prompts are reusable templates that collect GitLab data and return structured context to guide a workflow. In short, resources and prompts add context, while tools change state.

What is the difference between a static resource and a resource template?

A static resource is a fixed URI that always points to the same thing, such as gitlab://user/current. A resource template contains placeholders like {project_id} or {group_id} that the client fills in at request time to read a specific project, group, issue, or merge request. MCP lists fixed resources through resources/list and templates through resources/templates/list, so a client that inspects only resources/list sees the 45 resources as 8 fixed URIs plus 37 templates.

Can I disable resources and prompts?

Yes. The CAPABILITY_SURFACE setting controls which capabilities are registered. The default full registers resources, workflow guides, prompts, and the surface-aware gitlab://tools manifest. Setting CAPABILITY_SURFACE=minimal keeps only the gitlab://tools manifest — useful when a client does not consume resources or prompts and you want a smaller capability surface.

How many resources and prompts are available?

The server exposes 45 resources (8 fixed URIs plus 37 URI templates) and 37 prompt templates organized into categories such as core MR analysis, cross-project dashboards, team reports, analytics, and audits. The exact counts are generated from the server’s live capability registration, so this page stays in sync with the running server.