Integrates with Artifact Hub for automatic gadget discovery, allowing users to find and use Inspektor Gadget tools without manual configuration.
Uses Docker to run Inspektor Gadget tools within Kubernetes environments, enabling container-level monitoring and debugging capabilities.
Connects with GitHub for issue tracking and resource access, supporting the troubleshooting workflow.
Provides AI-powered debugging and inspection capabilities for Kubernetes clusters using Inspektor Gadget, enabling troubleshooting, traffic monitoring, and management of cluster resources.
Provides communication channel access through Slack for support and community interaction related to Inspektor Gadget.
Inspektor Gadget MCP Server
AI-powered debugging and inspection for Kubernetes clusters using 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
fileConfigure 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
Binary
You can head to the Releases page and download the latest binary for your platform:
After downloading, you can run the following command to add it to your VS Code MCP configuration.
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.
Gadget Discovery
Gadget discovery allows controlling which gadgets are available for use. You can choose between two methods:
Automatic: Uses Artifact Hub (
-gadget-discoverer=artifacthub
)Manual: Specify gadgets directly (
-gadget-images=trace_dns:latest
)
See INSTALL.md for configuration options.
Security Notes
Requires read-only access to your kubeconfig file
Needs network access for Artifact Hub discovery
See security guide for setting up server with minimal permissions
Resources
Related Projects
Inspektor Gadget - Kubernetes debugging tool
MCP Specification - Model Context Protocol
License
Apache License 2.0 - see LICENSE for details.
This server cannot be installed
Debug your Container and Kubernetes workloads with an AI interface powered by eBPF
Related MCP Servers
- AsecurityAlicenseAqualityTypeScript implementation of Kubernetes cluster operations for pods, deployments, services.Last updated -214,3371,098MIT License
- MIT License
- MIT License
- AsecurityAlicenseAqualityProvides Node.js debugging capabilities with process management for AI agents, allowing them to start/stop Node.js processes, set breakpoints, step through code, and evaluate expressions.Last updated -811MIT License