@giauphan/codeatlas-mcp
v1.2.4
Published
MCP server for CodeAtlas — exposes code analysis data to AI assistants via Model Context Protocol
Maintainers
Readme
🗺️ CodeAtlas MCP Server
A standalone MCP server that exposes CodeAtlas analysis data to AI assistants — Gemini, Claude, Cursor, Windsurf, and more.
⚡ Quick Start
1. Analyze your project
Install the CodeAtlas VS Code extension, then run:
Ctrl+Shift+P → CodeAtlas: Analyze ProjectThis generates .codeatlas/analysis.json in your project root.
2. Add MCP config
Copy the JSON block below into one of these files depending on your AI assistant:
| AI Assistant | Config file |
|---|---|
| Gemini | .gemini/settings.json |
| Claude Desktop | claude_desktop_config.json |
| Cursor | .cursor/mcp.json |
| Windsurf | .windsurf/mcp.json |
{
"mcpServers": {
"codeatlas": {
"command": "npx",
"args": ["-y", "@giauphan/codeatlas-mcp"]
}
}
}That's it! Your AI assistant can now query your codebase structure, dependencies, and insights.
🛠️ Available Tools
| Tool | Description |
|------|-------------|
| list_projects | List all analyzed projects (auto-discovers ~/) |
| get_project_structure | Get modules, classes, functions, variables |
| get_dependencies | Get import / call / containment relationships |
| get_insights | Get AI-generated code quality insights |
| search_entities | Search functions, classes by name (fuzzy match) |
| get_file_entities | Get all entities defined in a specific file |
📦 Alternative: Global Install
If you prefer installing globally instead of using npx:
npm install -g @giauphan/codeatlas-mcpThen update your MCP config to:
{
"mcpServers": {
"codeatlas": {
"command": "codeatlas-mcp"
}
}
}🔧 Environment Variables
| Variable | Description |
|----------|-------------|
| CODEATLAS_PROJECT_DIR | Force a specific project directory |
By default, the server auto-discovers all projects with
.codeatlas/analysis.jsonunder your home directory.
🧑💻 Development
git clone https://github.com/giauphan/codeatlas-mcp.git
cd codeatlas-mcp
npm install
npm run build
npm start