diff --git a/README.md b/README.md
index f1931ac..b7f12fd 100644
--- a/README.md
+++ b/README.md
@@ -1,11 +1,18 @@
# devcontainer-mcp
[](https://github.com/aniongithub/devcontainer-mcp/actions/workflows/ci.yml)
+[](https://www.anonline.me/devcontainer-mcp)
**Give your AI agent its own dev environment — not yours.**
`devcontainer-mcp` is an MCP server that lets AI coding agents create, manage, and work inside [dev containers](https://containers.dev/) across three backends: local Docker, [DevPod](https://devpod.sh/), and [GitHub Codespaces](https://github.com/features/codespaces). The agent builds, tests, and ships code in an isolated container — your laptop stays clean.
+
+
+
+
+> Works with **GitHub Copilot**, **Claude**, **Cursor**, and any MCP-compatible client.
+
## The Problem
When AI agents write code, they need to run it somewhere. Today that means your host machine:
@@ -14,6 +21,7 @@ When AI agents write code, they need to run it somewhere. Today that means your
- 🔴 **"Works on my machine"** — agents assume your local toolchain matches production
- 🔴 **No isolation** — one project's dependencies break another
- 🔴 **Security risk** — agents run arbitrary commands with your user privileges
+- 🔴 **Hardware constraints** — you're limited to your local machine's resources
## The Solution
@@ -36,6 +44,10 @@ Agent: "Let me build this project..."
## Quick Install
+
+
+
+
### Linux / macOS
```bash
@@ -79,6 +91,10 @@ graph TD
## Three Backends, One Interface
+
+
+
+
| Backend | Best for | Requires | Auth needed? |
|---------|----------|----------|:---:|
| **devcontainer CLI** (`devcontainer_*`) | Local Docker — fast, simple | [@devcontainers/cli](https://github.com/devcontainers/cli) + Docker | No |