Harvester HCI
Harvester MCP Server enables AI assistants like Claude Desktop and Cursor to interact with Harvester HCI clusters through a standardized protocol. Built in Go using the mark3labs/mcp-go SDK, it provides tools for managing both standard Kubernetes resources (pods, deployments, services) and Harvester-specific resources (virtual machines, images, volumes, networks). The server automatically connects to Kubernetes clusters using standard configuration paths and formats output in human-readable formats, making it ideal for DevOps teams who need AI assistance with Harvester cluster management and monitoring.
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/starbops/harvester-mcp-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Harvester HCI 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.