GitLab MCP (glab)
Provides GitLab issue and CI/CD management tools using the glab CLI, with reduced context token usage compared to the official GitLab MCP.
README
@greenfinity/gitlab-mcp
MCP server for GitLab issue and CI/CD management using the glab CLI.
Motivation
The official GitLab MCP (glab mcp serve) exposes 250+ tools, consuming significant context tokens (~25k) when used with Claude. This minimal MCP wrapper exposes only essential issue and CI/CD management tools (15 tools, ~6-8k tokens), reducing context usage by approximately 70%.
This server wraps the glab CLI to provide issue and CI/CD management functionality without the overhead of the full GitLab MCP toolset.
Requirements
- glab CLI installed and authenticated
- Node.js 22+
Installation
npm install @greenfinity/gitlab-mcp
Or run directly with npx:
npx @greenfinity/gitlab-mcp
Usage
With Claude Desktop
Add to your Claude Desktop configuration:
{
"mcpServers": {
"gitlab": {
"command": "npx",
"args": ["@greenfinity/gitlab-mcp"],
"env": {
"GITLAB_HOST": "gitlab.example.com"
}
}
}
}
With Claude Code
Add to your ~/.claude.json:
{
"mcpServers": {
"gitlab": {
"type": "stdio",
"command": "node",
"args": ["/path/to/gitlab-mcp/src/Cli.bs.mjs"],
"env": {
"GITLAB_HOST": "gitlab.example.com"
}
}
}
}
Supported Tools (15 total)
Issue Management (7 tools)
issue_list- List project issues with filters (state, labels, assignee, author, search)issue_view- View details of a specific issue by IDissue_create- Create a new issueissue_update- Update an existing issueissue_close- Close an issueissue_reopen- Reopen a closed issueissue_note- Add a comment/note to an issue
CI/CD Pipeline Management (5 tools)
pipeline_list- List CI/CD pipelines with filters (status, ref/branch)pipeline_view- View details of a specific pipeline including jobspipeline_create- Trigger a new pipeline runpipeline_cancel- Cancel a running pipelinepipeline_retry- Retry a failed pipeline
CI/CD Job Management (3 tools)
job_list- List jobs in a pipelinejob_view- View job details and log outputjob_retry- Retry a specific failed job
Why ReScript?
This package is implemented in ReScript, a functional language that compiles to JavaScript. ReScript offers a sound type system, excellent pattern matching, and produces clean, readable JavaScript output with no runtime overhead.
The compiled JavaScript is included in the npm package, so you can use this as a regular JavaScript module without any additional tooling.
Local Development
For local development:
# Install dependencies
yarn install
# Build the ReScript sources to JavaScript
yarn build
# Watch mode for development
yarn rescript:dev
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.