What is an MCP Server?

MCP (Model Context Protocol) server acts as a bridge, allowing AI models to access and interact with external data sources and tools. It standardizes how applications provide context to LLMs.

What are the prerequisites for using this server?

You need Python 3.10 or higher, the Git command-line tool in your PATH, and optionally a GitHub Personal Access Token for private repos.

How do I install the server?

Create a virtual environment, activate it, and then run `pip install -e .`

How do I use it with VS Code?

Add the server configuration to your VS Code settings (JSON) or create a `.vscode/mcp.json` file, specifying the path to the Python interpreter and the server script.

Is a GitHub Personal Access Token required?

It's only required if you want to analyze private GitHub repositories.

Does it support monorepos?

Yes, it can handle monorepo structures.

Where can I learn more about UBOS?

Visit the UBOS website at [https://ubos.tech](https://ubos.tech) to explore the full capabilities of our AI Agent development platform.

Repo Analyzer MCP Server (Local)

Q: What does the Repo Analyzer MCP Server do?

It analyzes Git repositories and provides Dockerfile creation guidance.

An MCP server that analyzes Git repositories and provides Dockerfile creation guidance. Runs locally using stdio transport.

Features

Analyzes repository structure and dependencies
Detects primary programming language
Identifies exposed ports
Handles monorepo detection
Supports private GitHub repositories (with GITHUB_TOKEN)
Provides detailed Dockerfile recommendations

Prerequisites

Python >= 3.10
Git command-line tool in PATH
(Optional) GitHub Personal Access Token for private repos

Installation

Create and activate a virtual environment:

python -m venv .venv
source .venv/bin/activate  # Linux/macOS
# or
.venvScriptsactivate     # Windows

Install dependencies:

pip install -e .

Usage

With MCP Inspector

mcp-inspector python src/repo_analyzer_mcp/server.py

With VS Code / GitHub Copilot

Add to VS Code settings (JSON) or create .vscode/mcp.json:

{
  "mcp.servers": {
    "repo-analyzer-local": {
      "type": "stdio",
      "command": "/path/to/venv/python",
      "args": ["/path/to/src/repo_analyzer_mcp/server.py"],
      "env": {
        "GITHUB_TOKEN": "${env:GITHUB_TOKEN}"
      },
      "displayName": "Repo Analyzer (Local)"
    }
  }
}

Replace /path/to/ with actual paths on your system.