Claude Code Architecture
How Claude Code reads your repository, calls tools through MCP, and edits code from the terminal.
Free to start · Fully editable · Export to SVG, PNG, GIF & MP4
What's in this template
6 connected components you can rename, recolor, and extend with AI.
This diagram shows how Claude Code — Anthropic’s agentic coding tool — fits together. At the center is the terminal agent. It is powered by a Claude model, reads and writes the files in your Git repository, and runs commands in your shell. It reaches the outside world through MCP (Model Context Protocol) servers and your installed tooling, and integrates with your editor so changes show up live in VS Code.
Use it to explain agentic coding to your team, to document how an AI assistant is wired into your developer workflow, or to plan which MCP servers and tools to expose. Every node is editable, so you can map it to your exact setup.
Great for
- Explaining agentic coding to your team
- Documenting an AI developer workflow
- Planning which MCP servers to expose
- Onboarding engineers to AI tooling
- Conference talk on AI coding agents
Frequently asked questions
What is Claude Code?+
Claude Code is Anthropic’s agentic coding tool that runs in your terminal. It uses a Claude model to read your codebase, run commands, call tools and edit files directly, acting like a pair programmer that can take actions.
How does Claude Code connect to other tools?+
It uses MCP (Model Context Protocol) servers plus your installed CLI tooling. MCP gives the agent a standard way to access data sources and external services such as databases, issue trackers and browsers.
Does Claude Code work with my editor?+
Yes. It integrates with editors like VS Code so the agent’s edits appear in your IDE, while still running from the terminal against your real repository.
Can I adapt this diagram to my setup?+
Absolutely. Rename nodes, add the specific MCP servers and tools you use, change the look, and export to PNG, SVG, GIF or MP4.
Related templates
View all AI & ML →How LLMs Work
A clear map of how large language models turn a prompt into an answer — and the models and hardware behind them
Codex Architecture
How an AI coding agent like Codex plans, writes and tests code inside a secure sandbox
RAG Architecture Diagram
Map how retrieval-augmented generation grounds an LLM in your data with a vector database
AI Agent Architecture Diagram
Visualize the reasoning loop, tools, and memory that let an AI agent plan and act
ML Training Pipeline Diagram
Chart every stage from raw data to a trained, validated machine learning model
LLM Application Architecture Diagram
See how a production LLM app wires frontend, orchestration, model APIs, and guardrails
Recommendation System Architecture Diagram
Show how candidate generation, ranking, and filtering produce personalized recommendations
MLOps Pipeline Diagram
Trace the flow from training and CI/CD to deployment, monitoring, and retraining
Make it yours in seconds
Open the claude code architecture in the Infogiph canvas, then edit, animate, and export.
Use this template