Gitlab Mcp Server
About
Model Context Protocol (MCP) server for GitLab — exposes 1006 GitLab REST & GraphQL API operations as MCP tools (28 meta-tools / 43 enterprise), 24 resources, 38 prompts, and 17 completion types for AI assistants. Written in Go, single static binary, stdio and HTTP transport.
Details
- Transport
- SSE
- License
- MIT
Explore
- Plain-language GitLab – the AI translates natural requests into API calls.
- 1000+ tools covering the full GitLab platform (REST + GraphQL).
- Low-token default dynamic surface (exposes 2 tools, reaches the full catalog).
- Proven with real models – 99.5% aggregate success across thousands of operations.
- Safe by design – read-only mode, safe mode (dry-run preview), and TLS options.
- Runs anywhere – one static binary or container; amd64 & arm64; stdio and HTTP.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Gitlab Mcp ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Pick one. Each path ends with you typing a prompt to your assistant.
<table>
<tr>
<th align="left">Client</th>
<th align="left">One-click button</th>
<th align="left">Token step</th>
</tr>
<tr>
<td><b>VS Code</b></td>
<td><a href="https://insiders.vscode.dev/redirect/mcp/install?name=gitlab&config=%7B%22command%22%3A%22docker%22%2C%22args%22%3A%5B%22run%22%2C%22-i%22%2C%22--rm%22%2C%22-e%22%2C%22GITLAB_TOKEN%22%2C%22ghcr.io%2Fjmrplens%2Fgitlab-mcp-server%3Alatest%22%2C%22--http%3Dfalse%22%5D%2C%22env%22%3A%7B%22GITLAB_TOKEN%22%3A%22%24%7Binput%3Agitlab_token%7D%22%7D%2C%22inputs%22%3A%5B%7B%22id%22%3A%22gitlab_token%22%2C%22type%22%3A%22promptString%22%2C%22description%22%3A%22GitLab%20Personal%20Access%20Token%20%28api%20scope%29%22%2C%22password%22%3Atrue%7D%5D%7D">
<td>prompts you (masked)</td>
</tr>
<tr>
<td><b>VS Code Insiders</b></td>
<td><a href="https://insiders.vscode.dev/redirect/mcp/install?name=gitlab&config=%7B%22command%22%3A%22docker%22%2C%22args%22%3A%5B%22run%22%2C%22-i%22%2C%22--rm%22%2C%22-e%22%2C%22GITLAB_TOKEN%22%2C%22ghcr.io%2Fjmrplens%2Fgitlab-mcp-server%3Alatest%22%2C%22--http%3Dfalse%22%5D%2C%22env%22%3A%7B%22GITLAB_TOKEN%22%3A%22%24%7Binput%3Agitlab_token%7D%22%7D%2C%22inputs%22%3A%5B%7B%22id%22%3A%22gitlab_token%22%2C%22type%22%3A%22promptString%22%2C%22description%22%3A%22GitLab%20Personal%20Access%20Token%20%28api%20scope%29%22%2C%22password%22%3Atrue%7D%5D%7D&quality=insiders">
<td>prompts you (masked)</td>
</tr>
<tr>
<td><b>Cursor</b></td>
<td><a href="https://cursor.com/install-mcp?name=gitlab&config=eyJjb21tYW5kIjoiZG9ja2VyIiwiYXJncyI6WyJydW4iLCItaSIsIi0tcm0iLCItZSIsIkdJVExBQl9UT0tFTiIsImdoY3IuaW8vam1ycGxlbnMvZ2l0bGFiLW1jcC1zZXJ2ZXI6bGF0ZXN0IiwiLS1odHRwPWZhbHNlIl0sImVudiI6eyJHSVRMQUJfVE9LRU4iOiJZT1VSX0dJVExBQl9UT0tFTiJ9fQ%3D%3D">
</a></td>
<td>edit <code>YOUR_GITLAB_TOKEN</code></td>
</tr>
<tr>
<td><b>LM Studio</b></td>
<td><a href="https://lmstudio.ai/install-mcp?name=gitlab&config=eyJjb21tYW5kIjoiZG9ja2VyIiwiYXJncyI6WyJydW4iLCItaSIsIi0tcm0iLCItZSIsIkdJVExBQl9UT0tFTiIsImdoY3IuaW8vam1ycGxlbnMvZ2l0bGFiLW1jcC1zZXJ2ZXI6bGF0ZXN0IiwiLS1odHRwPWZhbHNlIl0sImVudiI6eyJHSVRMQUJfVE9LRU4iOiJZT1VSX0dJVExBQl9UT0tFTiJ9fQ%3D%3D">
</a></td>
<td>edit <code>YOUR_GITLAB_TOKEN</code></td>
</tr>
<tr>
<td><b>Kiro</b></td>
<td><a href="https://kiro.dev/launch/mcp/add?name=gitlab&config=%7B%22command%22%3A%22docker%22%2C%22args%22%3A%5B%22run%22%2C%22-i%22%2C%22--rm%22%2C%22-e%22%2C%22GITLAB_TOKEN%22%2C%22ghcr.io%2Fjmrplens%2Fgitlab-mcp-server%3Alatest%22%2C%22--http%3Dfalse%22%5D%2C%22env%22%3A%7B%22GITLAB_TOKEN%22%3A%22YOUR_GITLAB_TOKEN%22%7D%7D">
</a></td>
<td>edit <code>YOUR_GITLAB_TOKEN</code></td>
</tr>
<tr>
<td><b>Claude Desktop</b></td>
<td><a href="https://github.com/jmrplens/gitlab-mcp-server/releases/latest/download/gitlab-mcp-server.mcpb">
<td>settings UI (keychain)</td>
</tr>
</table>
Each button registers the Docker-based server (auto-pulls the image on first run; you need Docker installed). The Claude Desktop row instead downloads a native .mcpb desktop extension (macOS universal + Windows, no Docker) — open it with Claude Desktop and fill in the settings. Need a token? Create a Personal Access Token with the api scope. Self-managed GitLab? Add a GITLAB_URL env var in your client's MCP config after install.
The binary ships a setup wizard that collects your GitLab token and configures your MCP client for you — ideal if you'd rather not edit JSON:
gitlab-mcp-server --setup
It auto-detects VS Code, Claude Desktop, Claude Code, Cursor, and Windsurf and writes the right config. On Windows, double-click the .exe to launch it.
Surface
Visible tools
Provider
Model
Anthropic
`claude-haiku-4-5-20251001`
Google
`gemini-flash-latest`
OpenAI
`gpt-5.4-nano`
Qwen
`qwen3.6-flash`
The server can present GitLab in three shapes, controlled by TOOL_SURFACE. The default needs no configuration.
| Surface | Visible tools | Best for |
| ----------------------------- | ------------------------------------------------- | ---------------------------------------------------------------- |
| Dynamic (default) | 2 (gitlab_find_action, gitlab_execute_action) | Lowest token cost; reaches the full catalog via find/execute. |
| Meta-tools (meta) | 32 base / 49 Ultimate / 50 GitLab.com Ultimate | Domain-grouped dispatchers with an action parameter. |
| Individual (individual) | ~847 Free/CE · ~999 Premium · 1065–1071 Ultimate | One MCP tool per GitLab operation; needs a large context window. |
Tool counts scale with your GitLab edition (GITLAB_TIER); higher tiers expose more actions. See Dynamic Toolset and Meta-Tools Reference for the ranking model, safety guards, and full catalogs. For dynamic runs where resources dominate context, set CAPABILITY_SURFACE=minimal.
The project includes an automated evaluator for model-facing MCP quality. It runs schema-only checks against the tool catalog or executes validated model tool calls through MCP against Docker GitLab CE or licensed Enterprise instances populated with fixtures. It measures whether each model chooses the correct action, sends valid parameters, recovers from actionable GitLab errors, and respects destructive-action safeguards — across Anthropic, Google, OpenAI, and Qwen.
<!-- START MODEL EVAL DYNAMIC SUMMARY -->
Current published result: Docker CE dynamic 20260627-232303.
| Provider | Model | Compatibility | Tool accuracy | Recovery | Docker live status |
| --------- | --------------------------- | ------------- | ------------: | ------------: | --------------------------- |
| Anthropic | claude-haiku-4-5-20251001 | OK | 100.0% | 100.0% (2/2) | 100.0% final across 555 ops |
| Google | gemini-flash-latest | OK | 100.0% | 100.0% (4/4) | 100.0% final across 555 ops |
| OpenAI | gpt-5.4-nano | Review | 99.3% | 84.6% (11/13) | 98.0% final across 555 ops |
| Qwen | qwen3.6-flash | OK | 100.0% | 100.0% (5/5) | 100.0% final across 555 ops |
The published model-evaluation set covers 596 task attempts and 2220 expected MCP operations. Across the selected reports, models emitted 2265 tool calls over 2265 model requests, with 99.5% aggregate final success. See AI Model Evaluation Results for the detailed current matrix.
<!-- END MODEL EVAL DYNAMIC SUMMARY -->
<details>
<summary>Enterprise meta & dynamic evaluation results</summary>
<!-- START MODEL EVAL ENTERPRISE META SUMMARY -->
Current published result: Docker Enterprise meta 20260527.
| Provider | Model | Compatibility | Tool accuracy | Recovery | Docker live status |
| --------- | --------------------------- | ------------- | ------------: | -----------: | -------------------------- |
| Anthropic | claude-haiku-4-5-20251001 | OK | 100.0% | 100.0% (1/1) | 100.0% final across 84 ops |
| Google | gemini-flash-latest | Review | 78.2% | 100.0% (7/7) | 100.0% final across 84 ops |
| OpenAI | gpt-5.4-nano | Review | 100.0% | 100.0% (4/4) | 100.0% final across 84 ops |
| Qwen | qwen3.6-flash | OK | 100.0% | 100.0% (1/1) | 100.0% final across 84 ops |
The published model-evaluation set covers 92 task attempts and 336 expected MCP operations. Across the selected reports, models emitted 345 tool calls over 350 model requests, with 100.0% aggregate final success. See AI Model Evaluation Results for the detailed current matrix.
<!-- END MODEL EVAL ENTERPRISE META SUMMARY -->
<!-- START MODEL EVAL ENTERPRISE DYNAMIC SUMMARY -->
Current published result: Docker Enterprise dynamic 20260628-015421.
| Provider | Model | Compatibility | Tool accuracy | Recovery | Docker live status |
| --------- | --------------------------- | ------------- | ------------: | -----------: | --------------------------- |
| Anthropic | claude-haiku-4-5-20251001 | OK | 100.0% | 100.0% (1/1) | 100.0% final across 202 ops |
| Google | gemini-flash-latest | OK | 100.0% | 100.0% (2/2) | 100.0% final across 202 ops |
| OpenAI | gpt-5.4-nano | OK | 100.0% | No repairs | 100.0% final across 202 ops |
| Qwen | qwen3.6-flash | OK | 100.0% | 100.0% (1/1) | 100.0% final across 202 ops |
The published model-evaluation set covers 124 task attempts and 808 expected MCP operations. Across the selected reports, models emitted 817 tool calls over 817 model requests, with 100.0% aggregate final success. See AI Model Evaluation Results for the detailed current matrix.
<!-- END MODEL EVAL ENTERPRISE DYNAMIC SUMMARY -->
</details>
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"gitlab mcp server": {
"gitlab-mcp-server-jmrplens": {
"command": "docker",
"args": [
"pull",
"ghcr.io/jmrplens/gitlab-mcp-server:latest"
]
}
}
}
}McpServers
{
"gitlab-mcp-server-jmrplens": {
"command": "docker",
"args": [
"pull",
"ghcr.io/jmrplens/gitlab-mcp-server:latest"
]
}
}<p align="center">
</p>
Connect your AI assistant to GitLab so it can review merge requests, triage pipelines, manage issues, and draft releases — in plain language. One static binary (or a container), 1000+ GitLab tools over the full REST + GraphQL API, working with Claude, Cursor, VS Code, and any MCP client.
You talk to your AI assistant; it does the GitLab work. No project IDs, API endpoints, or JSON to remember.
> "Review merge request !15 — is it safe to merge?" · "Why did the last pipeline fail?" · "List open issues assigned to me" · "Generate release notes from v1.0 to v2.0"
---
> 🤖 Using an AI assistant? Give it this repository URL and ask it to install the server for your client. Everything a model needs to do it headlessly — the declarative per-client config, claude mcp add one-liners, and defaults — is in llms.txt (no interactive wizard required).
Install in 60 seconds
Pick one. Each path ends with you typing a prompt to your assistant.
One-click install
<table>
<tr>
<th align="left">Client</th>
<th align="left">One-click button</th>
<th align="left">Token step</th>
</tr>
<tr>
<td><b>VS Code</b></td>
<td><a href="https://insiders.vscode.dev/redirect/mcp/install?name=gitlab&config=%7B%22command%22%3A%22docker%22%2C%22args%22%3A%5B%22run%22%2C%22-i%22%2C%22--rm%22%2C%22-e%22%2C%22GITLAB_TOKEN%22%2C%22ghcr.io%2Fjmrplens%2Fgitlab-mcp-server%3Alatest%22%2C%22--http%3Dfalse%22%5D%2C%22env%22%3A%7B%22GITLAB_TOKEN%22%3A%22%24%7Binput%3Agitlab_token%7D%22%7D%2C%22inputs%22%3A%5B%7B%22id%22%3A%22gitlab_token%22%2C%22type%22%3A%22promptString%22%2C%22description%22%3A%22GitLab%20Personal%20Access%20Token%20%28api%20scope%29%22%2C%22password%22%3Atrue%7D%5D%7D">
<td>prompts you (masked)</td>
</tr>
<tr>
<td><b>VS Code Insiders</b></td>
<td><a href="https://insiders.vscode.dev/redirect/mcp/install?name=gitlab&config=%7B%22command%22%3A%22docker%22%2C%22args%22%3A%5B%22run%22%2C%22-i%22%2C%22--rm%22%2C%22-e%22%2C%22GITLAB_TOKEN%22%2C%22ghcr.io%2Fjmrplens%2Fgitlab-mcp-server%3Alatest%22%2C%22--http%3Dfalse%22%5D%2C%22env%22%3A%7B%22GITLAB_TOKEN%22%3A%22%24%7Binput%3Agitlab_token%7D%22%7D%2C%22inputs%22%3A%5B%7B%22id%22%3A%22gitlab_token%22%2C%22type%22%3A%22promptString%22%2C%22description%22%3A%22GitLab%20Personal%20Access%20Token%20%28api%20scope%29%22%2C%22password%22%3Atrue%7D%5D%7D&quality=insiders">
<td>prompts you (masked)</td>
</tr>
<tr>
<td><b>Cursor</b></td>
<td><a href="https://cursor.com/install-mcp?name=gitlab&config=eyJjb21tYW5kIjoiZG9ja2VyIiwiYXJncyI6WyJydW4iLCItaSIsIi0tcm0iLCItZSIsIkdJVExBQl9UT0tFTiIsImdoY3IuaW8vam1ycGxlbnMvZ2l0bGFiLW1jcC1zZXJ2ZXI6bGF0ZXN0IiwiLS1odHRwPWZhbHNlIl0sImVudiI6eyJHSVRMQUJfVE9LRU4iOiJZT1VSX0dJVExBQl9UT0tFTiJ9fQ%3D%3D"></a></td>
<td>edit <code>YOUR_GITLAB_TOKEN</code></td>
</tr>
<tr>
<td><b>LM Studio</b></td>
<td><a href="https://lmstudio.ai/install-mcp?name=gitlab&config=eyJjb21tYW5kIjoiZG9ja2VyIiwiYXJncyI6WyJydW4iLCItaSIsIi0tcm0iLCItZSIsIkdJVExBQl9UT0tFTiIsImdoY3IuaW8vam1ycGxlbnMvZ2l0bGFiLW1jcC1zZXJ2ZXI6bGF0ZXN0IiwiLS1odHRwPWZhbHNlIl0sImVudiI6eyJHSVRMQUJfVE9LRU4iOiJZT1VSX0dJVExBQl9UT0tFTiJ9fQ%3D%3D"></a></td>
<td>edit <code>YOUR_GITLAB_TOKEN</code></td>
</tr>
<tr>
<td><b>Kiro</b></td>
<td><a href="https://kiro.dev/launch/mcp/add?name=gitlab&config=%7B%22command%22%3A%22docker%22%2C%22args%22%3A%5B%22run%22%2C%22-i%22%2C%22--rm%22%2C%22-e%22%2C%22GITLAB_TOKEN%22%2C%22ghcr.io%2Fjmrplens%2Fgitlab-mcp-server%3Alatest%22%2C%22--http%3Dfalse%22%5D%2C%22env%22%3A%7B%22GITLAB_TOKEN%22%3A%22YOUR_GITLAB_TOKEN%22%7D%7D"></a></td>
<td>edit <code>YOUR_GITLAB_TOKEN</code></td>
</tr>
<tr>
<td><b>Claude Desktop</b></td>
<td><a href="https://github.com/jmrplens/gitlab-mcp-server/releases/latest/download/gitlab-mcp-server.mcpb">
<td>settings UI (keychain)</td>
</tr>
</table>
Each button registers the Docker-based server (auto-pulls the image on first run; you need Docker installed). The Claude Desktop row instead downloads a native .mcpb desktop extension (macOS universal + Windows, no Docker) — open it with Claude Desktop and fill in the settings. Need a token? Create a Personal Access Token with the api scope. Self-managed GitLab? Add a GITLAB_URL env var in your client's MCP config after install.
Claude Code (claude mcp add)
Docker (no install — pulls the image on first run):
claude mcp add gitlab --env GITLAB_TOKEN=glpat-xxxx --transport stdio \
-- docker run -i --rm -e GITLAB_TOKEN ghcr.io/jmrplens/gitlab-mcp-server:latest --http=false
Or install the native binary first, then register it:
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
