Inspektor Gadget is a DevOps MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent debug container and Kubernetes workloads with eBPF. Install in 1 minute with mcpizy install inspektor-gadget.
DevOps
Debug container and Kubernetes workloads with eBPF. Deep system observability.
mcpizy install inspektor-gadgetnpx -y @inspektor-gadget/mcpMCP server for Azure DevOps. Manage repos, pipelines, work items, and pull requests.
Manage Buildkite pipelines and builds. Monitor CI/CD status and trigger deployments.
Enable AI agents to fix build failures from CircleCI. Debug CI pipelines and analyze test results.
Official MCP server for dbt (data build tool). Manage models, run transformations, query semantic layer.
If Inspektor Gadget doesn't fit your stack, these DevOps MCP servers solve similar problems.
The Inspektor Gadget MCP server is an DevOps Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents debug container and Kubernetes workloads with eBPF. It exposes Inspektor Gadget's capabilities as tools the AI can call directly from your editor or CLI.
The fastest way is the MCPizy CLI: run `mcpizy install inspektor-gadget` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y @inspektor-gadget/mcp` and restarting Claude Code.
Yes. The Inspektor Gadget MCP server is free and open source (see the GitHub repository linked on this page). You may still need a Inspektor Gadget account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.
Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.
Once installed, your AI agent can debug container and Kubernetes workloads with eBPF directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run Inspektor Gadget operations, inspect results, chain Inspektor Gadget with other MCP servers (see our Workflow Recipes), and automate repetitive devops tasks without leaving your editor.