longhorn-mcp
Related Servers
Alternatives to longhorn-mcp
No user-submitted related servers found.
Related Servers
- AlicenseBqualityCmaintenanceModel Context Protocol (MCP) server for the Rancher ecosystem: multi-cluster Kubernetes, Harvester HCI (VMs, storage, networks), and Fleet GitOps.1012Apache 2.0
- AlicenseAqualityBmaintenanceEnables MCP-compatible clients like Claude Desktop, Claude Code, Codex, and local-model hosts to inspect Proxmox VE clusters, nodes, VMs, containers, storage, snapshots, and tasks, with opt-in write operations for starting, stopping, cloning, backing up, and migrating guests. Read-only by default, it supports both stdio and Streamable HTTP transports.14MIT
- AlicenseNot gradedqualityDmaintenanceA standalone MCP server that exposes Rancher-side tools, forwards Authorization headers or uses configured credentials, and supports HTTP and stdio transports.MIT
- FlicenseAqualityDmaintenanceA Model Context Protocol (MCP) server that exposes the Rancher Manager v2.x API to LLM clients.113-
- AlicenseAqualityBmaintenanceMCP server for Proxmox VE and Proxmox Datacenter Manager, covering every API endpoint via six consolidated tools for list, describe, and call operations with a read-only safety gate.616 npm2AGPL 3.0
- AlicenseBqualityAmaintenanceMCP server for the Hetzner Cloud API. Manage servers, networks, volumes, firewalls, load balancers, and more through the Model Context Protocol.185161 npm4Functional Source , Version 1.1, MIT Future
TDQS
Scored across 104 tools
Multiple tool groups are explicit duplicates or near-duplicates: volume_snapshot_create is described as 'equivalent to' volume_snapshot_cr_create, and there are three snapshot-list paths (snapshot_list, volume_snapshot_list, volume_snapshot_cr_list) plus duplicate backup getters (backup_get vs backupvolume_backup_get). An agent must read fine-print warnings about write-access requirements to avoid selecting the wrong accessor.
The dominant resource_action pattern (volume_list, node_get, setting_update, backuptarget_create) is consistent and predictable. Deviations are mostly the longhorn_* meta tools (longhorn_list_tags, longhorn_raw_request) which place the verb in the middle rather than the end, plus minor oddities like volume_recurring_job_add using 'add' instead of 'create'.
104 tools is extreme by any standard, placing this far beyond the 50+ threshold. While Longhorn is a genuinely broad system, much of the bloat comes from redundant surface variants (volume-scoped vs global vs CRD-backed accessors for the same snapshot/backup data) rather than distinct capabilities, and the presence of a raw_request escape hatch further suggests the set is uncurated.
Coverage of the Longhorn domain is remarkably deep: full lifecycle for volumes, snapshots, backups, backing images, engine images, recurring jobs, system backup/restore, nodes, and settings. Notable gaps exist though — there is no restore-backup-to-volume tool and support bundles only have list/get (no create) — but the longhorn_raw_request escape hatch mitigates these dead ends.