Enables AI assistants to understand GitLab repositories through on-demand source code discovery and analysis, including locating relevant code, explaining relationships, and summarizing architecture without requiring embeddings or vector databases.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@gitlab-agent-mcp analyze the login module in project 42"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
gitlab-agent-mcp is an MCP server that enables AI assistants to understand GitLab repositories through targeted source code discovery and analysis.
Related MCP server: code-intel-mcp
The project was designed to answer repository-specific questions without requiring:
Model fine-tuning
RAG pipelines
Embedding generation
Vector databases
Repository indexing jobs
Instead, the system performs on-demand repository analysis using GitLab's native search capabilities combined with specialized AI agents.
Provide repository-aware answers using the latest source code directly from GitLab.
Reduce operational complexity by eliminating vector databases and embedding pipelines.
Avoid model fine-tuning for every repository or project.
Minimize token usage by retrieving only relevant files instead of loading the entire repository.
Enable AI assistants to understand implementation details, architecture, and code relationships.
Keep repository knowledge up to date without reindexing or retraining.
Locate relevant source code from natural language questions.
Discover implementation examples.
Explain relationships between files and components.
Summarize repository architecture.
Identify important classes, functions, and modules.
Provide contextual information to MCP-compatible AI assistants.
Responsible for understanding the developer's question and generating relevant source code search keywords.
Input:
Developer question
Output:
Search keywords
Example:
Question/Instruction:
Implement JWT functionality and make the project with id = 6358 as a reference
Keywords:
JWT
login
tokenYou can find the Project ID on the main page of the project.
Responsible for analyzing GitLab search results and selecting the most relevant files for the given question.
Input:
Developer question
GitLab search results
Output:
Relevant file candidates
Responsible for analyzing the selected source files and producing a technical summary, important findings, and code references.
Input:
Developer question
Source code context
Output:
Technical summary
Important files
Key findings
Relevant code examples
Python version 3.13+
uv venv
source .venv/bin/activate
uv syncThe application is configured using environment variables.
Example:
GITLAB_URL=https://gitlab.com
GITLAB_TOKEN=glxx-NA-xxxxxxxxxxxxxxxxx
OPENAI_USE_TRANSPORT=true
OPENAI_BASE_URL=https://api.openai.com/v1
OPENAI_API_KEY=xxxxx
DISCOVERY_MODEL=gpt-5.5
RELEVANCE_MODEL=gpt-5.5
ANALYSIS_MODEL=gpt-5.5
MAX_SEARCH_RESULTS=20
MAX_FILES=5
MAX_FILE_CHARS=15000
PORT=8000Variable | Description |
| GitLab server URL. |
| Personal Access Token used to access repositories and source code. |
Variable | Description |
| Base URL of an OpenAI-compatible API endpoint. |
| API key used to authenticate requests. |
| Enables custom transport for providers that require non-standard authentication headers. |
The project is provider-agnostic and supports any LLM service that exposes an OpenAI-compatible API.
Examples include:
OpenAI
Azure OpenAI
Ollama
vLLM
LiteLLM
OpenRouter
Local inference gateways
Internal enterprise AI platforms
Example configurations:
OpenAI
OPENAI_BASE_URL=https://api.openai.com/v1
OPENAI_API_KEY=sk-xxxxxxxxOllama
OPENAI_BASE_URL=http://localhost:11434/v1
OPENAI_API_KEY=dummyInternal Gateway
OPENAI_BASE_URL=https://llm.company.com/v1
OPENAI_API_KEY=xxxxxxxxVariable | Description |
| Model used by the Repository Discovery Agent. |
| Model used by the Code Relevance Agent. |
| Model used by the Repository Analysis Agent. |
Models can be different or identical depending on deployment requirements.
Variable | Description |
| Maximum number of GitLab search results retrieved before reranking. |
| Maximum number of files selected for analysis. |
| Maximum number of characters loaded from each file. |
Variable | Description |
| MCP server listening port. |
Make sure all required environment variable are set.
python main.py Build image
docker build -t gitlab-agent-mcp .Running
docker run --rm --env-file .env -p 8000:8000 gitlab-agent-mcpTest with MCP Inspector:
npx -y @modelcontextprotocol/inspector
Installing gitlab-agent-mcp to Claude Code
claude mcp add --transport http mcp_server_code_analyzer http://localhost:8000/mcpTest with Claude Code
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
An MCP server that gives your AI access to the source code and docs of all public github repos
A MCP server built for developers enabling Git based project management with project and personal…
Driflyte MCP server which lets AI assistants query topic-specific knowledge from web and GitHub.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/telkomdev/gitlab-agent-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server