harvester-mcp-server

starbops/harvester-mcp-server

3.1

If you are the rightful owner of harvester-mcp-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

Model Context Protocol (MCP) server for Harvester HCI that enables Claude Desktop, Cursor, and other AI assistants to interact with Harvester clusters through the MCP protocol.

Harvester MCP Server is a Go implementation of the Model Context Protocol (MCP) specifically designed for Harvester HCI. It allows AI assistants like Claude Desktop and Cursor to perform CRUD operations on Harvester clusters, which are essentially Kubernetes clusters with Harvester-specific CRDs. The server translates natural language requests from AI assistants into specific Kubernetes operations, interacts with the Kubernetes API of the Harvester cluster, and formats the results into human-readable text optimized for LLM consumption. This architecture enables AI assistants to interact with Harvester clusters through natural language, making complex Kubernetes operations more accessible to users.

Features

  • Kubernetes Core Resources: Supports operations like List, Get, Delete for Pods, Deployments, Services, Namespaces, Nodes, and CRDs.
  • Harvester-Specific Resources: Supports operations like List, Get for Virtual Machines, Images, Volumes, and Networks.
  • Enhanced User Experience: Provides human-readable formatted outputs, automatic grouping of resources, concise summaries, and detailed views.