Ig MCP Server

Inspektor Gadget MCP Server is an AI-driven debugging and inspection tool for Kubernetes clusters, providing one-click deployment, intelligent analysis, and automatic discovery functions.

Developer tools Monitoring #Kubernetes debugging #AI analysis #One-click deployment #Cluster monitoring .Go

rating : 2.5 points

downloads : 7.0K

update time : 2025-08-15

Open Site

What is Inspektor Gadget MCP Server?

Inspektor Gadget MCP Server is an AI-enhanced debugging tool for Kubernetes clusters. It provides intelligent cluster monitoring and troubleshooting capabilities through the Model Context Protocol (MCP). It can automatically deploy Inspektor Gadget to your Kubernetes cluster and offer an intuitive AI interaction interface to analyze cluster behavior.

How to use Inspektor Gadget MCP Server?

You can interact with the MCP server through VS Code Copilot Chat and use natural language commands to perform various debugging tasks. The server supports one-click deployment of Inspektor Gadget to the cluster and provides a variety of pre-built debugging tools (gadgets).

Applicable scenarios

Suitable for scenarios such as real-time monitoring of Kubernetes clusters, network problem diagnosis, security auditing, performance analysis, and daily operation and maintenance debugging. It is especially suitable for DevOps teams and SRE engineers who need to quickly locate complex problems.

Main features

AI-enhanced interface

Simplify the Kubernetes debugging process through natural language interaction, and automatically analyze and summarize the output results of tools

One-click deployment

Deploy and uninstall Inspektor Gadget in the cluster with simple commands

Automatic tool discovery

Support automatic discovery of available tools (gadgets) from Artifact Hub, or manually specify the required tool set

Multi-running mode

Support foreground debugging mode and background monitoring mode to meet the needs of different scenarios

Advantages

Lower the threshold of Kubernetes debugging and simplify complex operations through natural language interaction

A rich set of pre-built tools covering monitoring needs in multiple aspects such as network, security, and performance

Flexible deployment options, supporting both Docker and local binary running methods

Active community support and continuous updates

Limitations

Requires access to the kubeconfig file, with certain security considerations

Some advanced features require a specific version of the Kubernetes cluster to support

The AI analysis results may not be completely accurate and need manual verification

How to use

Prepare the environment

Ensure that Docker is installed and the kubeconfig file is configured

Configure the MCP server

Add the MCP server configuration in VS Code and choose to use Docker or the local binary method

Start using

Enter natural language commands in VS Code Copilot Chat to interact with the server

Usage examples

Diagnose DNS problems

When there are domain name resolution problems in the services in the cluster, you can use the trace_dns tool to view the specific DNS query situation

Network connection analysis

Analyze the network connection situation between services to discover abnormal connections or performance bottlenecks

Frequently asked questions

What permissions does the MCP server need?

How to limit the available tools (gadgets)?

Does it support the Windows system?

Related resources

Official documentation

Complete documentation for using Inspektor Gadget

GitHub repository

Project source code and issue tracking

Slack channel

Communicate with developers and other users

Usage examples

Detailed usage cases and examples

🚀 Inspektor Gadget MCP Server

Leverage AI for debugging and inspection in Kubernetes clusters with Inspektor Gadget.

https://github.com/user-attachments/assets/86367982-c0aa-455c-ac9e-ca43348899df

✨ Features

AI-powered interface for Kubernetes troubleshooting and monitoring.
One-click Inspektor Gadget deployment and removal.
Intelligent output summarization and analysis.
Automatic gadget discovery from Artifact Hub.

🚀 Quick Start

Ensure you have Docker and a valid kubeconfig file.
Configure the MCP server in VS Code (see INSTALL.md).
Start using AI commands in VS Code Copilot Chat.
Try: "Show me DNS traffic" or "Deploy Inspektor Gadget".
Head to examples for detailed examples.

📦 Installation

You can use the following commands to quickly configure the Inspektor Gadget MCP server using either Docker or a binary in your VS Code settings.

Docker

Install Inspektor Gadget MCP Server - Artifact Hub Discovery

```bash code --add-mcp '{ "name": "inspektor-gadget", "command": "docker", "args": [ "run", "-i", "--rm", "--mount", "type=bind,src=${env:HOME}/.kube/config,dst=/kubeconfig", "ghcr.io/inspektor-gadget/ig-mcp-server:latest", "-gadget-discoverer=artifacthub" ] }' ```

Install Inspektor Gadget MCP Server - Specific Gadgets

Binary

You can head to the Releases page and download the latest binary for your platform:

Linux

```bash MCP_VERSION=$(curl -s https://api.github.com/repos/inspektor-gadget/ig-mcp-server/releases/latest | jq -r .tag_name) MCP_ARCH=amd64 curl -sL https://github.com/inspektor-gadget/ig-mcp-server/releases/download/${MCP_VERSION}/ig-mcp-server-linux-${MCP_ARCH}.tar.gz | sudo tar -C /usr/local/bin -xzf - ig-mcp-server ```

macOS

```bash MCP_VERSION=$(curl -s https://api.github.com/repos/inspektor-gadget/ig-mcp-server/releases/latest | jq -r .tag_name) MCP_ARCH=arm64 curl -sL https://github.com/inspektor-gadget/ig-mcp-server/releases/download/${MCP_VERSION}/ig-mcp-server-darwin-${MCP_ARCH}.tar.gz | sudo tar -C /usr/local/bin -xzf - ig-mcp-server ```

Windows

```powershell $MCP_VERSION = (curl.exe -s https://api.github.com/repos/inspektor-gadget/ig-mcp-server/releases/latest | ConvertFrom-Json).tag_name $MCP_ARCH = "amd64" curl.exe -L "https://github.com/inspektor-gadget/ig-mcp-server/releases/download/$MCP_VERSION/ig-mcp-server-windows-$MCP_ARCH.tar.gz" -o "ig-mcp-server.tar.gz" $destPath = "C:\Program Files\ig-mcp-server" if (-Not (Test-Path $destPath -PathType Container)) { mkdir $destPath} tar.exe -xzf "ig-mcp-server.tar.gz" -C "$destPath" rm ig-mcp-server.tar.gz Write-Host "✅ Extracted to $destPath" Write-Host "👉 Please add '$destPath' to your PATH environment variable manually." ```

After downloading, you can run the following command to add it to your VS Code MCP configuration.

Install Inspektor Gadget MCP Server - Artifact Hub Discovery

```bash code --add-mcp '{ "name": "inspektor-gadget", "command": "ig-mcp-server", "args": [ "-gadget-discoverer=artifacthub" ] }' ```

Install Inspektor Gadget MCP Server - Specific Gadgets

```bash code --add-mcp '{ "name": "inspektor-gadget", "command": "ig-mcp-server", "args": [ "-gadget-images=trace_dns:latest,trace_tcp:latest" ] }' ```

📚 Documentation

Available Tools

Management Tools

is_inspektor_gadget_deployed: Checks if Inspektor Gadget is deployed in your cluster.
deploy_inspektor_gadget: Installs Inspektor Gadget in your cluster (skipped if -read-only is set).
undeploy_inspektor_gadget: Removes Inspektor Gadget from your cluster (skipped if -read-only is set).

Lifecycle Tools

stop-gadget: Stops a background running gadget.
get-results: Retrieves results from a background running gadget.
wait: Waits for a gadget to finish running.

Dynamic Tools

Each gadget is registered as its own MCP tool (e.g., trace_dns, trace_tcp, etc.) and supports running gadgets in foreground mode, which is useful for debugging/development and also in background mode for observability.

Also, you can control which gadgets are available by configuring the MCP server with the -gadget-discoverer or -gadget-images options, allowing you to limit the tools to only those you need.