The CodeAtlas MCP Server exposes codebase analysis data to AI assistants, enabling them to query project structure, dependencies, and AI-generated insights.
List Projects (list_projects): Discover all CodeAtlas-analyzed projects under your home directory, returning their names, paths, and last analysis timestamps.
Get Project Structure (get_project_structure): Retrieve all modules, classes, functions, and variables in a project, with optional filtering by entity type and result limits.
Get Dependencies (get_dependencies): Explore import, call, and containment relationships between entities, with filtering by source, target, and relationship type.
Get Insights (get_insights): Access AI-generated code quality insights including refactoring suggestions, security issues, and maintainability analysis.
Search Entities (search_entities): Fuzzy search for functions, classes, modules, or variables by name across a project, with optional type filtering.
Get File Entities (get_file_entities): Retrieve all classes, functions, and variables defined within a specific file using partial path matching.
Compatible with major AI tools including Gemini, Claude, Cursor, Windsurf, and VS Code Copilot. Supports both npx execution and global installation.
Click on "Deploy 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., "@CodeAtlas MCP Server show the module structure and dependencies for the current project"
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.
Give your AI assistant deep understanding of any codebase
A standalone MCP server that exposes code analysis data to Gemini, Claude, Cursor, Windsurf, VS Code Copilot — with persistent AI memory between conversations.
Your Code → CodeAtlas Analyze → MCP Server → AI Understands Everything
│
10 powerful tools:
• Search functions & classes
• Trace feature flows
• Generate architecture diagrams
• Persistent memory across conversationsBefore CodeAtlas: AI greps blindly, forgets your project every conversation. After CodeAtlas: AI instantly knows your architecture, dependencies, and remembers context.
Related MCP server: code-intel MCP Server
Install the CodeAtlas extension, then:
Ctrl+Shift+P → CodeAtlas: Analyze Project{
"mcpServers": {
"codeatlas": {
"command": "npx",
"args": ["-y", "@giauphan/codeatlas-mcp"]
}
}
}{
"mcpServers": {
"codeatlas": {
"command": "npx",
"args": ["-y", "@giauphan/codeatlas-mcp"]
}
}
}{
"mcp": {
"servers": {
"codeatlas": {
"command": "npx",
"args": ["-y", "@giauphan/codeatlas-mcp"]
}
}
}
}{
"mcpServers": {
"codeatlas": {
"command": "npx",
"args": ["-y", "@giauphan/codeatlas-mcp"]
}
}
}claude mcp add codeatlas -- npx -y @giauphan/codeatlas-mcp{
"mcpServers": {
"codeatlas": {
"command": "npx",
"args": ["-y", "@giauphan/codeatlas-mcp"]
}
}
}Done! Your AI can now use all 10 CodeAtlas tools.
Tool | Description | Example Use |
| List all analyzed projects | "What projects do I have?" |
| Get modules, classes, functions | "Show me all classes" |
| Import/call/containment relationships | "What does UserService depend on?" |
| Code quality & security analysis | "Any security issues?" |
| Fuzzy search entities by name | "Find the login function" |
| All entities in a specific file | "What's in auth.ts?" |
Tool | Description | Example Use |
| Mermaid architecture diagram (module imports) | "Show me the system architecture" |
| Mermaid execution flow diagram (call chains) | "How does the payment feature work?" |
Tool | Description | Example Use |
| Save context to | "Remember what we changed" |
| Trace feature through codebase | "What files are involved in auth?" |
AI assistants forget everything between conversations. CodeAtlas fixes this:
Conversation 1 → AI analyzes code → sync_system_memory
│
.agents/memory/
├── system-map.md ← Architecture diagram
├── modules.json ← All entities
├── conventions.md ← Code patterns
├── business-rules.json ← Domain logic
├── feature-flows.json ← Feature traces
└── change-log.json ← Change history
│
Conversation 2 → AI reads memory → full context restored instantly ✨When you run Analyze Project, CodeAtlas auto-creates rule files for your AI IDE:
Generated File | For |
| All AI assistants |
| Cursor |
| Claude Code |
| Windsurf |
These tell your AI to:
Read .agents/memory/ at the start of every conversation
Use MCP tools before making changes
Call sync_system_memory after completing changes
Language | Features |
TypeScript / JavaScript | Full AST: imports, classes, functions, variables, calls, implements |
Python | Classes, functions, variables, imports, calls |
PHP | Classes, interfaces, traits, enums, functions, properties |
Blade Templates |
|
npm install -g @giauphan/codeatlas-mcpThen use "command": "codeatlas-mcp" in your MCP config (no args needed).
Variable | Description |
| Force a specific project directory |
By default, the server auto-discovers all projects with
.codeatlas/analysis.jsonunder~/.
git clone https://github.com/giauphan/codeatlas-mcp.git
cd codeatlas-mcp
npm install
npm run build
npm test # 6 tests
npm start # Start MCP serverCodeAtlas Extension — VS Code extension with interactive code graph
MCP Protocol — Model Context Protocol standard
MIT — Free for personal and commercial use.
Generate a Mermaid diagram showing the EXECUTION FLOW of a feature. Unlike generate_system_flow (which shows module imports), this traces the actual call chain: entry point → controller → service → model → database. Given a keyword, it finds all related functions and classes, then builds a flowchart or sequence diagram showing how they call each other at runtime. This is the best tool for understanding HOW a feature works step-by-step.
Inputs: keyword (required), project, diagramType, depth, +1 more.
Auto-generate a Mermaid flowchart diagram showing how modules, classes, and functions connect in the system. Returns a Mermaid diagram string that AI can read to understand the full system flow without reading every file.
Inputs: project, scope, feature, maxNodes.
Get import/call/containment/implements relationships between entities. Shows how modules, classes, and functions are connected.
Inputs: project, source, target, relationship, +1 more.
Get all entities (classes, functions, variables) defined in a specific file.
Inputs: filePath (required), project.
Get AI-generated code insights including refactoring suggestions, security issues, and maintainability analysis.
Inputs: no named parameters.
Get all modules, classes, functions, and variables in the analyzed project. Returns entity type, name, file path, and line number.
Inputs: project, type, limit.
List all projects that have been analyzed by CodeAtlas. Returns project names, paths, and last analysis time.
Inputs: no named parameters.
Search for functions, classes, modules, or variables by name. Supports fuzzy matching.
Inputs: query (required), project, type.
Create or update the .agents/memory/ folder with auto-generated system documentation. This folder serves as AI's 'long-term memory' — it persists between conversations. After calling this, AI in any future conversation can read these files to understand the full system flow without re-analyzing. Call this after completing any code changes.
Inputs: project, businessRule, changeDescription.
Trace the complete flow of a feature through the codebase. Given a keyword (e.g. 'login', 'payment', 'crawl'), finds all related files, classes, and functions, then orders them by dependency chain to show the execution flow. This helps AI understand which files to read when working on a feature.
Inputs: keyword (required), project, depth.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 10 tools
Most tools have distinct purposes. However, `generate_feature_flow_diagram` and `trace_feature_flow` both trace feature flow by keyword, differing only in output format (diagram vs. ordered list). Descriptions help differentiate, but an agent might still select the wrong one for a given need.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., `generate_feature_flow_diagram`, `get_dependencies`, `list_projects`). No mixed conventions or vague verbs.
With 10 tools, the set covers the domain of code analysis and documentation well. Each tool serves a distinct, necessary function without redundancy or bloat.
The tool surface covers core CRUD-like operations for projects and entities, plus advanced analysis (flows, insights, memory sync). Minor gaps exist, such as no tool for editing entities or comparing versions, but core workflows are supported.
Search indexed code, trace dependencies, assess change impact, and recall repository memory.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
