# Claude Desktop

### What you'll accomplish

By the end of this guide, you'll have Opsera Agents running in Claude Code and ready to automate your DevSecOps workflows with natural language commands.

**You'll be able to:**

* Run security scans with a single command
* Generate CI/CD pipelines by describing what you need
* Analyze architecture and generate diagrams
* Audit compliance across your codebase

**Time to complete:** \~5 minutes

***

### Before you begin

Make sure you have:

* ✅ **Claude Code CLI** installed 
* ✅ **Terminal access** (macOS, Linux, or WSL)
* ✅ **Node.js 18+** installed (`node --version`)

That's it. No API keys, no complex configuration—just add one line and you're ready.

***

### Setup (choose your method)

#### Option 1: Install Opsera Agent from Claude Marketplace (Private Marketplace)

Install the Opsera DevSecOps plugin in Claude Code using `/install opsera-devsecops` (or manually via the plugin marketplace), then restart and authenticate via browser login.

Once installed, simply describe your task.

[Learn the installation procedure here.](/marketplace/marketplace/claude-code-plugin.md)

#### Option 2: One-line install (recommended)

Run this command in your terminal:

```bash
claude mcp add --scope user --transport http opsera https://agent.opsera.ai/mcp
```

Then restart Claude Code. Done.

**What this does:** Adds Opsera Agents to your Claude Code MCP configuration globally, so it works across all your projects.

#### Option 3: Manual configuration

If you prefer manual setup or need to customize:

1. **Open your MCP config file:**
   * macOS/Linux: `~/.config/claude/mcp_settings.json`
   * Or use: `claude mcp edit`
2. **Add this configuration:**

```json
{
  "mcpServers": {
    "opsera": {
      "type": "http",
      "url": "https://agent.opsera.ai/mcp"
    }
  }
}
```

3. **Save and restart Claude Code**

***

### Verify it's working

Open Claude Code and type:

```
"List available Opsera agents"
```

You should see the 4 core agents:

* Architecture Analyze Agent
* Security Scan Agent
* SQL Security Agent
* Compliance Audit Agent

If you see these, you're all set! 🎉

***

### Try your first agent

Once connected, just describe what you want in natural language:

**Run a security scan:**

```
"Run a security scan on my repository at ~/projects/my-app and show me critical vulnerabilities"
```

**Analyze architecture:**

```
"Analyze the architecture of my payment service and generate a system diagram"
```

**Check compliance:**

```
"Run a SOC2 compliance audit and show me what needs to be fixed"
```

***

### Troubleshooting

**"MCP server not found" error?**

* Restart Claude Code after adding the configuration
* Verify the config file was saved correctly
* Check Node.js is installed: `node --version`

**Agents not responding?**

* Make sure you're connected to the internet
* Try: `claude mcp list` to see installed servers
* Restart Claude Code


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.agents.opsera.ai/terminal-setup/claude-desktop.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.