kubectl
kubectl-mcp-tool is an MCP server that enables natural language interaction with Kubernetes clusters, allowing AI assistants like Cursor, Claude, and WindSurf to perform kubectl operations through conversational commands. Developed by Rohit Ghumare under the MIT license, it features a minimal wrapper approach for better compatibility across different MCP SDK versions, supports multiple transport protocols (stdio and SSE), and includes specialized implementations for various AI assistants. The tool translates natural language queries into kubectl commands, handles resource management operations, and provides diagnostic capabilities, making it particularly valuable for developers who want to manage their Kubernetes resources through AI assistants without memorizing complex kubectl syntax.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- cloud-infra
- Source
- PulseMCP
- Repository
- github.com/rohitg00/kubectl-mcp-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve kubectl from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.