Archaic MCP Server
Integrates Archaic's AI-powered architecture analysis with Claude Code, enabling interactive exploration of component connections, data flows, and system structure through natural language.
README
Archaic MCP Server
MCP server that brings Archaic architecture analysis and visualization into Claude Code.
Archaic analyzes your codebase and generates interactive architecture diagrams — showing how components connect, how data flows, and how your system is structured. This MCP server lets Claude Code read and interact with that architecture data directly in your terminal.
What is Archaic?
Archaic is an AI-powered architecture analysis tool that understands your codebase and generates:
- Architecture diagrams — components, services, databases, and how they connect
- Execution flows — request traces showing how data moves through your system
- Code maps — function-level dependency graphs
Download the desktop app (macOS) at tryarchaic.com.
Installation
npm install -g @archaic-ai/mcp
Claude Code setup
Add to your Claude Code config (~/.claude.json):
{
"mcpServers": {
"archaic": {
"command": "archaic-mcp"
}
}
}
Or for project-scoped config, add to .mcp.json in your project root.
You can also configure this directly from the Archaic desktop app under Settings > Claude Code Integration.
Tools
| Tool | Description |
|---|---|
get_desktop_architecture |
Read the current architecture from the desktop app |
update_architecture |
Push architecture changes to the live diagram |
create_task |
Create a task for the desktop app |
get_pending_task |
Check for pending tasks from the UI |
report_progress |
Send status updates to the desktop app |
complete_task |
Mark a task as done |
How It Works
The MCP server connects to the Archaic desktop app running locally. When Claude Code makes structural changes to your codebase, it can push updates to the architecture diagram in real-time.
The typical workflow:
- Open your project in Archaic Desktop and run an analysis
- Start Claude Code in your project — it connects to the MCP server automatically
- As Claude modifies code, it reads the architecture, creates tasks, and pushes diagram updates
- You see the architecture update live in the desktop app
Environment Variables
| Variable | Required | Default | Description |
|---|---|---|---|
ARCHAIC_DESKTOP_URL |
No | http://127.0.0.1:7432 |
Desktop app endpoint |
Example Usage
Once configured, you can ask Claude Code things like:
- "Show me the architecture of my project"
- "How does the authentication flow work?"
- "What components depend on the database service?"
- "Refactor the auth module and update the architecture"
Links
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.