Kubernetes Read-Only
This MCP server provides AI assistants with read-only access to Kubernetes clusters through a comprehensive set of tools for resource inspection, log retrieval, and metrics monitoring, built using Go with the Kubernetes client-go library and supporting both stdio and SSE transport modes. The implementation offers 10 tools including resource listing with filtering, detailed resource inspection, advanced pod log retrieval with grep patterns and time filtering, API resource discovery, context management, node and pod metrics collection, and base64 encoding utilities, all while maintaining strict read-only security to prevent destructive operations. Built with automatic connectivity validation, per-command context switching, and client-side pagination for metrics, it serves DevOps teams needing AI-assisted cluster troubleshooting, developers requiring safe cluster inspection capabilities, and organizations wanting to enable AI assistants to help diagnose Kubernetes issues without modification risks.
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
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Kubernetes Read-Only 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.