MCP Server

Let AI coding agents access your application monitoring data to help them debug your application.

The rise of AI coding agents like Claude Code, OpenCode, Cursor, and GitHub 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.

Local CLI Agents

The communication between your coding agent and Inspector needs authentication. Before moving forward you need to create an API key.

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

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

Cursor

{
  "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.

Web Chat AI Assistant

Using an AI Assistant on a web interfaceit's different. They authenticate external MCP servers through OAuth, the login-and-approve flow you already know from connecting Slack or Google Drive to some other tool, not through a secret you copy and paste.

Here is the actual flow, using Claude as the example, because it’s the client I use most. ChatGPT and other web based agents follow the same pattern under different menu names.

Step 1: add the connector with just a URL

In Claude, open Settings and go to the Connectors section, then choose to add a custom connector. You give it a name, Inspector, and paste the server URL, which you’ll find in your application settings inside the Inspector dashboard. It looks like this, with your own application ID at the end:

https://app.inspector.dev/mcp?app=YOUR_APP_ID

That’s it. You don’t need to touch “Advanced settings”, and there is no field asking you for an authorization token, because the server now negotiates that part on its own.

Step 2: authorize the connection on Inspector

As soon as you connect, you’re redirected to Inspector, where you’ll see a plain authorization screen telling you which application is asking for access and what it will be able to do. In this case, Claude requesting permission to use the MCP server. You log in with the Inspector account you already have, click Authorize, and the handshake completes behind the scenes.

Step 3: check the tools you just gave your assistant

You land back in Claude with a confirmation that you’re connected, and the connector page now shows the tools the Inspector MCP server exposes, along with a permission switch for each one. You’ll see the ability to analyze a specific error, pull recent errors from your production environment, list recent transactions, inspect the details of a single transaction, and get the ten worst performing transactions in your application.