GitLab
by modelcontextprotocol
GitLab API, enabling project management
What is GitLab
GitLab MCP Server
MCP Server for the GitLab API, enabling project management, file operations, and more.
Features
- Automatic Branch Creation: When creating/updating files or pushing changes, branches are automatically created if they don't exist
- Comprehensive Error Handling: Clear error messages for common issues
- Git History Preservation: Operations maintain proper Git history without force pushing
- Batch Operations: Support for both single-file and multi-file operations
Tools
-
create_or_update_file
- Create or update a single file in a project
- Inputs:
project_id
(string): Project ID or URL-encoded pathfile_path
(string): Path where to create/update the filecontent
(string): Content of the filecommit_message
(string): Commit messagebranch
(string): Branch to create/update the file inprevious_path
(optional string): Path of the file to move/rename
- Returns: File content and commit details
-
push_files
- Push multiple files in a single commit
- Inputs:
project_id
(string): Project ID or URL-encoded pathbranch
(string): Branch to push tofiles
(array): Files to push, each withfile_path
andcontent
commit_message
(string): Commit message
- Returns: Updated branch reference
-
search_repositories
- Search for GitLab projects
- Inputs:
search
(string): Search querypage
(optional number): Page number for paginationper_page
(optional number): Results per page (default 20)
- Returns: Project search results
-
create_repository
- Create a new GitLab project
- Inputs:
name
(string): Project namedescription
(optional string): Project descriptionvisibility
(optional string): 'private', 'internal', or 'public'initialize_with_readme
(optional boolean): Initialize with README
- Returns: Created project details
-
get_file_contents
- Get contents of a file or directory
- Inputs:
project_id
(string): Project ID or URL-encoded pathfile_path
(string): Path to file/directoryref
(optional string): Branch/tag/commit to get contents from
- Returns: File/directory contents
-
create_issue
- Create a new issue
- Inputs:
project_id
(string): Project ID or URL-encoded pathtitle
(string): Issue titledescription
(optional string): Issue descriptionassignee_ids
(optional number[]): User IDs to assignlabels
(optional string[]): Labels to addmilestone_id
(optional number): Milestone ID
- Returns: Created issue details
-
create_merge_request
- Create a new merge request
- Inputs:
project_id
(string): Project ID or URL-encoded pathtitle
(string): MR titledescription
(optional string): MR descriptionsource_branch
(string): Branch containing changestarget_branch
(string): Branch to merge intodraft
(optional boolean): Create as draft MRallow_collaboration
(optional boolean): Allow commits from upstream members
- Returns: Created merge request details
-
fork_repository
- Fork a project
- Inputs:
project_id
(string): Project ID or URL-encoded pathnamespace
(optional string): Namespace to fork to
- Returns: Forked project details
-
create_branch
- Create a new branch
- Inputs:
project_id
(string): Project ID or URL-encoded pathbranch
(string): Name for new branchref
(optional string): Source branch/commit for new branch
- Returns: Created branch reference
Setup
Personal Access Token
Create a GitLab Personal Access Token with appropriate permissions:
- Go to User Settings > Access Tokens in GitLab
- Select the required scopes:
api
for full API accessread_api
for read-only accessread_repository
andwrite_repository
for repository operations
- Create the token and save it securely
Usage with Claude Desktop
Add the following to your claude_desktop_config.json
:
Docker
{
"mcpServers": {
"gitlab": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"GITLAB_PERSONAL_ACCESS_TOKEN",
"-e",
"GITLAB_API_URL",
"mcp/gitlab"
],
"env": {
"GITLAB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>",
"GITLAB_API_URL": "https://gitlab.com/api/v4" // Optional, for self-hosted instances
}
}
}
}
NPX
{
"mcpServers": {
"gitlab": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-gitlab"
],
"env": {
"GITLAB_PERSONAL_ACCESS_TOKEN": "<YOUR_TOKEN>",
"GITLAB_API_URL": "https://gitlab.com/api/v4" // Optional, for self-hosted instances
}
}
}
}
Build
Docker build:
docker build -t vonwig/gitlab:mcp -f src/gitlab/Dockerfile .
Environment Variables
GITLAB_PERSONAL_ACCESS_TOKEN
: Your GitLab personal access token (required)GITLAB_API_URL
: Base URL for GitLab API (optional, defaults tohttps://gitlab.com/api/v4
)
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Leave a Comment
Comments section will be available soon. Stay tuned!
Frequently Asked Questions
What is MCP?
MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications, providing a standardized way to connect AI models to different data sources and tools.
What are MCP Servers?
MCP Servers are lightweight programs that expose specific capabilities through the standardized Model Context Protocol. They act as bridges between LLMs like Claude and various data sources or services, allowing secure access to files, databases, APIs, and other resources.
How do MCP Servers work?
MCP Servers follow a client-server architecture where a host application (like Claude Desktop) connects to multiple servers. Each server provides specific functionality through standardized endpoints and protocols, enabling Claude to access data and perform actions through the standardized protocol.
Are MCP Servers secure?
Yes, MCP Servers are designed with security in mind. They run locally with explicit configuration and permissions, require user approval for actions, and include built-in security features to prevent unauthorized access and ensure data privacy.
Related MCP Servers
Fetch
Web content fetching and conversion for efficient LLM usage
Playwright
A Model Context Protocol (MCP) server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages through structured accessibility snapshots, bypassing the need for screenshots or visually-tuned models.
puppeteer-mcp-server
Puppeteer
Browser automation and web scraping
Playwright Universal MCP
A universal Playwright MCP server for browser automation in containerized environments
MCP Server Playwright
MCP Server Playwright - A browser automation service for Claude Desktop
OneNote MCP Server
MCP server for browsing and interacting with OneNote web app using browser-use automation
Playwright
๐ Fetcher MCP - Playwright Headless Browser Server
MCP server for fetch web page content using Playwright headless browser.
MCP Browser
NeoForge Browser MCP server - used to test the frontend
Submit Your MCP Server
Share your MCP server with the community
Submit Now