# Gitlab AI connector guide

Connect Gitlab data to AI agents with Combined. Explore merge requests, users, issues, source setup, MCP access and read-only business queries.

Combined offers 1,125 connectors across catalog sources and connectors generated through desktop automation.

## Connect

1. Open Combined Connected Apps and select Gitlab.
2. Authorize the source and choose the relevant datasets.
3. Complete a first sync, then grant your agent access through the Set up or Access workspace.
4. Discover the actual source schemas before querying.

## Setup reference

- API URL: optional
- Authorization Method: required in the upstream source schema; OAuth2.0 or Private Token
- Access Token: depends on the selected authentication/setup option
- Client Id: depends on the selected authentication/setup option
- Client Secret: depends on the selected authentication/setup option
- Refresh Token: depends on the selected authentication/setup option
- Token Expiry Date: depends on the selected authentication/setup option
- Private Token: depends on the selected authentication/setup option
- Groups: optional
- Groups: optional
- Number of Concurrent Threads: optional
- Projects: optional
- Projects: optional
- Start Date: optional

## Dataset reference

- merge_requests; key: id
- users; key: name
- issues; key: id
- projects; key: id
- commits; key: id
- groups; key: id
- group_milestones; key: id
- group_members; key: group_id, id
- group_labels; key: group_id, id
- group_issue_boards; key: id
- epics; key: iid
- epic_issues; key: iid
- project_milestones; key: id
- project_members; key: project_id, id
- project_labels; key: project_id, id
- branches; key: project_id, name
- releases; key: name
- tags; key: project_id, name
- deployments; key: id
- merge_request_commits; key: id
- pipelines; key: id
- pipelines_extended; key: id
- jobs; key: id

This is the upstream connector reference, version 4.4.36. Account permissions and sync configuration determine the datasets available in your workspace.

## Agent prompt

Use Combined to analyze my Gitlab data.
List my granted sources, discover the datasets and describe their fields.
Look for datasets corresponding to merge_requests, users, issues, projects, commits, groups.
Check the last successful sync and report the available date coverage.
Propose three useful questions based on the fields actually available.
For the question I choose, run read-only SQL over the complete matching dataset.
Use a bounded result; include source names, time window and query receipt.
Ask for a missing join key or metric definition instead of inventing one.

## Links

- Combined: https://www.trycombined.com/
- Setup: https://www.trycombined.com/docs/getting-started/onboarding
- MCP: https://www.trycombined.com/docs/integrations/mcp
- Pricing: https://www.trycombined.com/pricing
- Upstream source reference: https://docs.airbyte.com/integrations/sources/gitlab
- Full guide: https://www.trycombined.com/connectors/gitlab