by harshmaur
Integrate with GitLab for seamless repository management, file operations, CI/CD, issue tracking, and merge requests via
Provides comprehensive access to GitLab repositories, issues, merge requests, and project events through natural language commands. Includes 86 tools covering the full GitLab API.
GitLab is a community-built MCP server published by harshmaur that provides AI assistants with tools and capabilities via the Model Context Protocol. Integrate with GitLab for seamless repository management, file operations, CI/CD, issue tracking, and merge requests via It is categorized under developer tools, productivity.
You can install GitLab in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
GitLab is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
I recommend GitLab for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
According to our notes, GitLab benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Useful MCP listing: GitLab is the kind of server we cite when onboarding engineers to host + tool permissions.
GitLab is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
GitLab is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
Strong directory entry: GitLab surfaces stars and publisher context so we could sanity-check maintenance before adopting.
According to our notes, GitLab benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
I recommend GitLab for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
GitLab reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
We evaluated GitLab against two servers with overlapping tools; this profile had the clearer scope statement.
showing 1-10 of 42
GitLab MCP(Model Context Protocol) Server. Includes bug fixes and improvements over the original GitLab MCP server.
<a href="https://glama.ai/mcp/servers/7jwbk4r6d7"><img width="380" height="200" src="https://glama.ai/mcp/servers/7jwbk4r6d7/badge" alt="gitlab mcp MCP server" /></a>
When using with the Claude App, you need to set up your API key and URLs directly.
{
"mcpServers": {
"GitLab communication server": {
"command": "npx",
"args": ["-y", "@zereight/mcp-gitlab"],
"env": {
"GITLAB_PERSONAL_ACCESS_TOKEN": "your_gitlab_token",
"GITLAB_API_URL": "your_gitlab_api_url",
"GITLAB_READ_ONLY_MODE": "false",
"USE_GITLAB_WIKI": "false", // use wiki api?
"USE_MILESTONE": "false", // use milestone api?
"USE_PIPELINE": "false" // use pipeline api?
}
}
}
}
{
"mcpServers": {
"GitLab communication server": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"GITLAB_PERSONAL_ACCESS_TOKEN",
"-e",
"GITLAB_API_URL",
"-e",
"GITLAB_READ_ONLY_MODE",
"-e",
"USE_GITLAB_WIKI",
"-e",
"USE_MILESTONE",
"-e",
"USE_PIPELINE",
"iwakitakuma/gitlab-mcp"
],
"env": {
"GITLAB_PERSONAL_ACCESS_TOKEN": "your_gitlab_token",
"GITLAB_API_URL": "https://gitlab.com/api/v4", // Optional, for self-hosted GitLab
"GITLAB_READ_ONLY_MODE": "false",
"USE_GITLAB_WIKI": "true",
"USE_MILESTONE": "true",
"USE_PIPELINE": "true"
}
}
}
}
docker run -i --rm \
-e GITLAB_PERSONAL_ACCESS_TOKEN=your_gitlab_token \
-e GITLAB_API_URL= "https://gitlab.com/api/v4"\
-e GITLAB_READ_ONLY_MODE=true \
-e USE_GITLAB_WIKI=true \
-e USE_MILESTONE=true \
-e USE_PIPELINE=true \
-e SSE=true \
-p 3333:3002 \
iwakitakuma/gitlab-mcp
{
"mcpServers": {
"GitLab communication server": {
"url": "http://localhost:3333/sse"
}
}
}
$ sh scripts/image_push.sh docker_user_name
GITLAB_PERSONAL_ACCESS_TOKEN: Your GitLab personal access token.GITLAB_API_URL: Your GitLab API URL. (Default: https://gitlab.com/api/v4)GITLAB_READ_ONLY_MODE: When set to 'true', restricts the server to only expose read-only operations. Useful for enhanced security or when write access is not needed. Also useful for using with Cursor and it's 40 tool limit.USE_GITLAB_WIKI: When set to 'true', enables the wiki-related tools (list_wiki_pages, get_wiki_page, create_wiki_page, update_wiki_page, delete_wiki_page). By default, wiki features are disabled.USE_MILESTONE: When set to 'true', enables the milestone-related tools (list_milestones, get_milestone, create_milestone, edit_milestone, delete_milestone, get_milestone_issue, get_milestone_merge_requests, promote_milestone, get_milestone_burndown_events). By default, milestone features are disabled.USE_PIPELINE: When set to 'true', enables the pipeline-related tools (list_pipelines, get_pipeline, list_pipeline_jobs, get_pipeline_job, get_pipeline_job_output, create_pipeline, retry_pipeline, cancel_pipeline). By default, pipeline features are disabled.+<!-- TOOLS-START -->
create_or_update_file - Create or update a single file in a GitLab projectsearch_repositories - Search for GitLab projectscreate_repository - Create a new GitLab projectget_file_contents - Get the contents of a file or directory from a GitLab projectpush_files - Push multiple files to a GitLab project in a single commitcreate_issue - Create a new issue in a GitLab projectcreate_merge_request - Create a new merge request in a GitLab projectfork_repository - Fork a GitLab project to your account or specified namespacecreate_branch - Create a new branch in a GitLab projectget_merge_request - Get details of a merge request (Either mergeRequestIid or branchName must be provided)get_merge_request_diffs - Get the changes/diffs of a merge request (Either mergeRequestIid or branchName must be provided)get_branch_diffs - Get the changes/diffs between two branches or commits in a GitLab projectupdate_merge_request - Update a merge request (Either mergeRequestIid or branchName must be provided)create_note - Create a new note (comment) to an issue or merge requestcreate_merge_request_thread - Create a new thread on a merge requestmr_discussions - List discussion items for a merge requestupdate_merge_request_note - Modify an existing merge request thread notecreate_merge_request_note - Add a new note to an existing merge request threadupdate_issue_note - Modify an existing issue thread notecreate_issue_note - Add a new note to an existing issue threadlist_issues - List issues in a GitLab project with filtering optionsget_issue - Get details of a specific issue in a GitLab projectupdate_issue - Update an issue in a GitLab projectdelete_issue - Delete an issue from a GitLab projectlist_issue_links - List all issue links for a specific issuelist_issue_discussions - List discussions for an issue in a GitLab projectget_issue_link - Get a specific issue linkcreate_issue_link - Create an issue link between two issuesdelete_issue_link - Delete an issue linklist_namespaces - List all namespaces available to the current userget_namespace - Get details of a namespace by ID or pathverify_namespace - Verify if a namespace path existsget_project - Get details of a specific projectlist_projects - List projects accessible by the current userlist_labels - List labels for a projectget_label - Get a single label from a projectcreate_label - Create a new label in a projectupdate_label - Update an existing label in a projectdelete_label - Delete a label from a projectlist_group_projects - List projects in a GitLab group with filtering optionslist_wiki_pages - List wiki pages in a GitLab projectget_wiki_page - Get details of a specific wiki pagecreate_wiki_page - Create a new wiki page in a GitLab projectupdate_wiki_page - Update an existing wiki page in a GitLab projectdelete_wiki_page - Delete a wiki page from a GitLab projectget_repository_tree - Get the repository tree for a GitLab project (list files and directories)list_pipelines - List pipelines in a GitLab project with filtering optionsget_pipeline - Get details of a specific pipeline in a GitLab projectlist_pipeline_jobs - List all jobs in a specific pipelineget_pipeline_job - Get details of a GitLab pipeline job numberget_pipeline_job_output - Get the output/trace of a GitLab pipeline job numbercreate_pipeline - Create a new pipeline for a branch or tagretry_pipeline - Retry a failed or canceled pipelinecancel_pipeline - Cancel a running pipelinelist_merge_requests - List merge requests in a GitLab project with filtering optionslist_milestones - List milestones in a GitLab project with filtering optionsget_milestone - Get details of a specific milestonecreate_milestone - Create a new milestone in a GitLab projectedit_milestone - Edit an existing milestone in a GitLab projectdelete_milestone - Delete a milestone from a GitLab projectget_milestone_issue - Get issues associated with a specific milestoneget_milestone_merge_requests - Get merge requests associated with a specific milestonepromote_milestone - Promote a milestone to the next stageget_milestone_burndown_events - Get burndown events for a specific milestoneget_users - Get GitLab user details by usernamesPrerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.