GitLab MCP connector
Connect GitLab to Elaichi and Claude, ChatGPT, Cursor, Microsoft Copilot, or any MCP client can read your projects, branches and merge requests, draft commits and reviews, and leave comments, with each person signed in as themselves and every call logged.
- Connects over OAuth
- Free 14-day trial
- No credit card
Summarize the open merge requests on the billing project.
Working in GitLab with Elaichi
-
Get mcp server version
-
Get project
-
Get merge request
How to connect GitLab to Claude, ChatGPT, Cursor or Microsoft Copilot
Step by step, for each AI app
GitLab MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
GitLab MCP connector for Claude Code
-
1
In a terminal, run
claude mcp addwith the endpoint.https://api.elaichi.ai/mcp -
2
Start Claude Code and run
/mcp. -
3
Pick elaichi, then sign in and approve in the browser.
Terminal
$ claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
Use --scope project instead to share it with the repository through .mcp.json.
GitLab MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web. The plugin directory lives at chatgpt.com/plugins.
GitLab MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
GitLab MCP connector for Microsoft Copilot
-
1
In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
-
2
Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
https://api.elaichi.ai/mcp -
3
Create a new connection, sign in and approve, then press Add to agent.
-
4
Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.
- Server URL
- https://api.elaichi.ai/mcp
- Authentication
- OAuth 2.0
- Type
- Dynamic discovery
Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.
Connect GitLab to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
What teams do with GitLab through Elaichi
Ask in plain English. Each person’s AI can do only what they’re allowed to, and every action it takes in GitLab is logged.
-
Engineering
Get the gist of a merge request first
Ask for a summary of a GitLab merge request, the commits behind it and the discussion so far, before you open the diff yourself.
-
Engineering
Start a fix without leaving the chat
Have the agent open a branch in the right GitLab project, commit the change you describe, and draft the merge request for you to check.
-
Engineering management
Catch up on what is waiting for review
List the open merge requests across your GitLab projects, see who they are assigned to and how long they have been sitting.
-
Release
Draft release notes from the commit history
Pull the commits that landed since the last GitLab release and turn them into notes a customer could read.
-
Support
Find out whether a fix has merged
Ask whether the merge request for a customer's bug has been accepted in GitLab and which release it went out in.
-
Security
Check who has access to a project
List the members of a GitLab project and their roles when an auditor asks, or when a contractor engagement ends.
Try asking
- “Summarize the open merge requests on the billing project.”
- “Which commits landed on main since the last release?”
- “Open a branch for the login fix and draft a merge request.”
What connecting GitLab gets you
6 screens from Elaichi, each doing one job for your GitLab account.
Ask Elaichi to work across your apps.
Summarize the open merge requests on the billing project.
Which commits landed on main since the last release?
Open a branch for the login fix and draft a merge request.
Also runs in Claude, ChatGPT, Cursor or Microsoft Copilot
The agent
Ask about merge requests in plain language.
Get answers from live GitLab projects, branches and commits without opening a tab.
Copy the endpoint
AI apps
One governed endpoint for every MCP client.
Use GitLab from Claude, ChatGPT, Cursor or Microsoft Copilot through one org endpoint, no shared API key.
Tool catalog
47 GitLab tools, no custom code required.
Projects, branches, commits, merge requests, reviews and releases, cataloged and ready to call.
Toolboxes
Each team gets its own GitLab toolbox.
Scope release, review and platform work to the teams that actually do it.
Shared connections
Teammates work through one GitLab connection.
Share a connection with a team and nobody else ever sees a token.
Audit log
Every GitLab call is logged, nothing is lost.
See who merged, committed or commented, when, and on which project.
From answering questions to doing the work
A trigger starts the work, inside the same permissions and the same audit log as everything else. Workflows, collections and live dashboards come with the Black plan.
GitLab digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch projects
GitLab
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Jake Morgan
Approve Deny -
Post the digest
GitLab
Queued
Workflows
A schedule starts the work, a person approves.
Open merge requests are fetched, grouped, drafted into a digest, approved, then posted back to GitLab.
GitLab health
Refreshed 4 minutes ago · every 15 minutes · from the projects collection
Projects
1,284 ↓ 12%
Merge requests
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Projects created
Last 14 days
By team
Share of activity
Platform 34%
Backend 27%
Frontend 21%
Mobile 18%
Collections and dashboards
GitLab health, computed on a schedule, no model.
Merge requests merged, commits over 14 days and a breakdown by team, refreshed automatically.
Why connect GitLab's MCP server through Elaichi
GitLab builds and runs this MCP server. Elaichi sits in front of it, so GitLab's tools follow the same sign-in, access rules and audit log as every other connector your organization uses. Calls an AI client makes to GitLab's server directly, outside Elaichi, get none of this.
-
One address for every AI client
Claude, ChatGPT, Cursor and Microsoft Copilot reach GitLab's tools at the same Elaichi address as every other connected app. Nobody adds GitLab's server to each client one by one.
-
Each person signs in as themselves
Each person signs in to Elaichi as themselves. Members connect with their own GitLab sign-in, and a connection someone shares runs on its owner's account. The credential stays in Elaichi's separate credential service, and the AI client holds only its Elaichi sign-in.
-
Rules checked before a call leaves
Restrictions on a role or a person, for the whole connector or a single tool, are checked before a call reaches GitLab's server. By default, a tool GitLab does not mark read-only or non-destructive counts as destructive, and over MCP it still runs under the "Use your connected apps" consent.
-
One audit log for every app
Each call that runs is recorded with the person, the tool, the connection and the AI client that made it, in the same audit log as every other app.
-
Tool issues go to GitLab
GitLab builds and runs these tools, and Elaichi staff do not curate them, so a report about how a tool behaves goes to the GitLab team.
For IT and engineering
Elaichi vs Zapier MCP vs Composio for GitLab
All three can connect GitLab to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over GitLab tools | Allow or restrict single GitLab tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per GitLab call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
GitLab tools for your AI agents
47 tools are ready to call through Elaichi's MCP endpoint the moment you connect GitLab, governed by the same roles, restrictions, and audit log as everything else in Elaichi. GitLab builds and runs these tools.
No tools match your search.
Questions, answered
How do I connect GitLab to Claude?
Connect GitLab in Elaichi first, which opens GitLab's own sign-in page so you authorize it with your usual account. There is no OAuth application to register and no client ID or secret to generate. Then in Claude go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. GitLab is then available in Claude the next time you start a conversation.
Does GitLab work with ChatGPT and Cursor as well as Claude?
Yes. Once GitLab is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any other MCP client and the Elaichi Agent. You connect GitLab once and every client you use picks it up.
What can an AI agent actually do with my GitLab data?
An agent connected to GitLab through Elaichi can look up projects, branches, commits, releases and repository files, list and summarize merge requests, and tell you who is a member of a project. It can also open a branch, add a commit, create or update a merge request, leave a review or a comment, accept a merge request, fork a repository, and start a session with GitLab Duo. Short, concrete asks such as "list open merge requests on the billing project" work better than long paragraphs.
Does connecting GitLab give the AI access to every project?
No. The AI acts as the person who signed in to GitLab, so it can only see the projects, groups and repositories that person can already see. Elaichi can narrow that access further by restricting which actions a role may use, but it can never widen it beyond what GitLab itself allows that person.
Can I stop an agent from merging or changing things in GitLab?
Yes. Restrictions in Elaichi apply per action, so you can allow reading merge requests and commits in GitLab while restricting accepting a merge request, adding a commit or forking a repository. A restricted action still appears in Elaichi's tool search, flagged as restricted, but Claude, ChatGPT, Cursor or Microsoft Copilot cannot run it, whatever the prompt says.
What happens to a GitLab connection when someone leaves?
Offboarding a person in Elaichi ends their access to GitLab through every AI client at once. If they had shared a GitLab connection with a team, that connection keeps working for everyone else. Disconnecting GitLab once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client at the same time.
Does the GitLab MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. GitLab is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for GitLab?
Yes. Both let Claude, ChatGPT or Cursor use GitLab. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every GitLab call.
How is Elaichi different from Composio for GitLab?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to GitLab: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put GitLab in front of your team
14 days of Black, no credit card. Connect it once and pick what each team can call.
When the trial ends, nothing is deleted. You move to the free Personal plan, and connections, roles and the audit log stay where they are.
Add one link to your AI app
The same link for everyone on your team.
https://api.elaichi.ai/mcp
ChatGPT
Claude
Cursor
Microsoft Copilot