> For the complete documentation index, see [llms.txt](https://docs.inspector.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.inspector.dev/concepts/mcp-server.md).

# MCP Server

The rise of AI coding agents like [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [OpenCode](https://opencode.ai/), [Cursor](https://cursor.com/), and [GitHub Copilot](https://github.com/features/copilot) has transformed how developers write code. These tools can generate entire features, debug complex issues, and refactor code at unprecedented speed - but their effectiveness depends heavily on how well they understand your issues.

Inspector MCP server allows AI clients to consume your application monitoring data, helping them spotlight the exact code changes needed to fix bugs and improve application performance.

### What the Inspector MCP Server Actually Does

The MCP server creates a bridge between AI code assistant and your Inspector monitoring data. Your AI assistant gains access to performance metrics, error analyses, database queries, and application health indicators.

They can investigate slow transactions, the execution timeline and performance data of everything happen into your application while running the actual production environment.

Rather than switching between multiple tools, you maintain a single conversation thread where coding questions and production monitoring blend seamlessly.

{% embed url="<https://www.youtube.com/watch?v=Z_BNykUXGb8>" %}

### Getting Started

The communication between your coding agent and Inspector needs authentication. Before moving forward you need to create an [**API key**](https://app.inspector.dev/account/api).

Navigate to your **Application Settings** in the Inspector dashboard to copy the proper configuration. Here are ready to use configurations for most commomn ai coding asisstant.

#### Claude Code

```
claude mcp add --transport http inspector https://app.inspector.dev/mcp?app=xxxx --header "Authorization: Bearer YOUR_API_KEY"
```

#### VS Code

```json
{
    "mcp": {
        "servers": {
            "inspector": {
                "type": "http",
                "url": "https://app.inspector.dev/mcp?app=xxxx",
                "headers": {
                    "Authorization": "Bearer YOUR_API_KEY"
                }
            }
        }
    }
}
```

#### Cursor

```json
{
  "mcpServers": {
    "inspector": {
      "url": "https://app.inspector.dev/mcp?app=xxxx",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
```

If you need to configure the MCP connection in other agent you need to setup two mandatory parameters:

* URL with the APP you want to connect (e.g. <https://app.inspector.dev/mcp?app=9583>)
* Authorization token

Verify the connection with a simple prompt, like: “*Are there errors in the app production environment?*”

Once connected, your AI assistant gains access to comprehensive monitoring data, including performance metrics, errors, bug fix suggestions, database query analysis, and more.