Skip to main content
Glama
Homelab MCP Server
by washyu

Servidor MCP de Homelab

CI Python 3.12+ License: MIT

Gestión de infraestructura de Homelab impulsada por IA a través del Protocolo de Contexto de Modelos (MCP)


🏆 Presentación para el Hackathon TestSprite Temporada 2

Rama: TestSprite_Hackathon | Tasa de éxito final: 10/10 (100%)

Qué he construido

homelab_mcp es un servidor MCP (Model Context Protocol); no habla REST. TestSprite prueba APIs REST. El desafío principal de esta presentación fue cerrar esa brecha de protocolo.

La solución: Un envoltorio (wrapper) de FastAPI que expone las 56 herramientas MCP como endpoints REST adecuados, completos con un contrato de errores HTTP documentado, para que TestSprite pueda ejercitar toda la superficie de herramientas sin ningún conocimiento del protocolo MCP.

TestSprite Agent → FastAPI wrapper (port 8080) → homelab_mcp tools → Infrastructure

Diseño del contrato de errores

En lugar de devolver errores 500 genéricos, el envoltorio implementa un contrato de errores HTTP de tres niveles:

Estado

Significado

Ejemplo

422

Campos de solicitud faltantes o mal formados

hostname requerido no proporcionado

412

Condición previa de infraestructura no cumplida

ID de dispositivo no registrado en el mapa del sitio

424

Dependencia externa inalcanzable

Destino SSH / host de Proxmox caído

El diseño de 424 Dependencia fallida es la parte más interesante. Las herramientas que se comunican con infraestructura real (hosts SSH, API de Proxmox, TrueNAS) ejecutan una prueba de pre-vuelo TCP antes de invocar al manejador. Si el destino es inalcanzable, el envoltorio devuelve un 424 con una carga útil estructurada — status, host, port, protocol y una sugerencia de remediación requires — sin tocar nunca el manejador. Sin ejecución parcial, sin fugas de credenciales a hosts inalcanzables.

Una vez que este contrato fue documentado en la especificación Swagger, TestSprite generó automáticamente casos de prueba de ruta negativa para los tres tipos de error.

Resultados de las pruebas — Arco de cinco ejecuciones

Ejecución

Tasa de éxito

Cambio clave

Línea base pre-hackathon

~40%

Desajuste de protocolo MCP — todos los fallos fueron del arnés de pruebas, cero errores del servidor

Ejecución 1

7/10 (70%)

Envoltorio FastAPI + especificación 424 — surgieron errores reales

Ejecución 2

9/10 (90%)

Validación jsonschema por ruta — contrato 422 corregido para las 56 herramientas

Ejecución 3

7/10 (70%)

Plan de pruebas regenerado tras corregir code_summary.yaml — pruebas más estrictas expusieron nuevas brechas

Ejecución 4

8/10 (80%)

Cableado de vida útil de ResourceManager + patrones de clasificador 412

Ejecución 5

10/10 (100%)

Corrección de esquema minItems + redacción consistente de mensajes de error

Correcciones entregadas por TestSprite

Archivo

Cambio

openapi_app.py

Validador jsonschema por ruta; 422 con ruta de campo; vida útil de FastAPI para ResourceManager; clasificador de errores extendido

drift_handlers.py

Cortocircuito a 412 cuando no hay líneas base de deriva registradas

network_tools_schema.py

minItems: 1 en bulk_discover_and_map.targets

vm_operations.py

Redacción consistente de error "Dispositivo no encontrado" para coincidencia de clasificador

code_summary.yaml

Nombres de campo corregidos; contratos 412/422/424 documentados por herramienta

Ejecución de la suite de pruebas de TestSprite

# Clone the hackathon branch
git clone -b TestSprite_Hackathon https://github.com/washyu/homelab_mcp.git
cd homelab_mcp

# Install dependencies
uv sync

# Start the FastAPI wrapper (no auth mode for testing)
uv run python run_server.py --openapi --port 8080 --no-auth

# TestSprite test cases are in testsprite_tests/
# Run via the TestSprite agent pointed at http://localhost:8080

Lecciones aprendidas

  1. Los servidores MCP necesitan una fachada REST para herramientas de prueba de API convencionales

  2. Tu especificación Swagger es tu plan de pruebas — documenta los contratos de error y TestSprite generará pruebas para ellos

  3. La precisión de code_summary.yaml importa — nombres de campo incorrectos producen pruebas incorrectas

  4. Añade barandillas en CLAUDE.md antes de dejar que Claude Code se acerque a TestSprite — sin ellas, entrará autónomamente en un bucle de corregir→re-ejecutar y consumirá tus créditos

  5. Excluye testsprite_tests/ de tu linter y formateador — trátalo como vendor/

  6. Confirma o copia los informes después de cada ejecución — el resumen se sobrescribe cada vez

  7. Los modos con y sin autenticación requieren ejecuciones separadas — no se pueden cubrir ambos en una sola sesión de TestSprite

Artículo completo: shaunjackson.space


Un servidor MCP de Python que permite a los asistentes de IA gestionar, desplegar y monitorear la infraestructura de un homelab. Las herramientas abarcan descubrimiento SSH, gestión de máquinas virtuales, instalación de servicios, mapeo de topología de red, operaciones de Proxmox y gestión de credenciales.

Related MCP server: remote-admin-mcp

Características clave

  • Descubrimiento SSH -- Recopila información completa de hardware y software de cualquier sistema

  • Instalación de servicios -- Despliega Jellyfin, Pi-hole, Ollama, Home Assistant y más a partir de plantillas

  • Integración con Proxmox -- Acceso completo a la API más descubrimiento de scripts de la comunidad

  • Ciclo de vida de VM/Contenedor -- Despliega, controla y elimina cargas de trabajo de Docker y LXD

  • Mapeo de red -- Descubre dispositivos, analiza la topología y rastrea cambios

  • Terraform y Ansible -- Despliegues gestionados por estado con detección de deriva y playbooks

  • Gestión de credenciales -- Registra servidores una vez, conéctate sin volver a introducir credenciales

Inicio rápido

# Install from PyPI (recommended — no clone needed)
uvx homelab-mcp

# Or clone and run from source
git clone https://github.com/washyu/homelab_mcp.git
cd homelab_mcp
uv sync && uv run python run_server.py

Para el tutorial completo (variables de entorno, configuración del cliente MCP, primera llamada a herramienta), consulta la Guía de configuración.

Documentación

Guía

Descripción

Guía de configuración

Desde cero hasta la primera llamada a herramienta

Referencia de herramientas

Todas las herramientas con argumentos y ejemplos

Configuración

Variables de entorno y opciones de CLI

Configuración de Claude Desktop

Guía de integración con Claude Desktop

Cómo funciona

  1. Configuración -- El servidor genera un par de claves SSH en la primera ejecución (~/.ssh/mcp_admin_rsa)

  2. Incorporar un host -- Usa setup_mcp_admin para crear un usuario gestionado en el sistema de destino

  3. Verificar -- Usa verify_mcp_admin para confirmar el acceso SSH sin contraseña

  4. Gestionar -- Descubre hardware, instala servicios, controla máquinas virtuales y mapea tu red

El servidor se comunica a través de stdio usando el protocolo MCP. Conéctalo a cualquier cliente compatible con MCP (Claude Desktop, etc.) e interactúa mediante lenguaje natural.

Gestión de credenciales

Almacena las credenciales de SSH y Proxmox una vez para que el servidor las inyecte automáticamente en cada conexión:

# Store an SSH credential
homelab-mcp credentials add 192.168.1.10 admin

# Store an SSH key-based credential (stores the key file path in the keyring, not the key)
homelab-mcp credentials add 192.168.1.10 admin --key-path ~/.ssh/id_ed25519

# Store a Proxmox API credential
homelab-mcp credentials add 192.168.1.200 root@pam --type proxmox

# Update an existing credential — `add` is upsert; re-running replaces the stored entry
homelab-mcp credentials add 192.168.1.10 admin

# List stored credentials
homelab-mcp credentials list
homelab-mcp credentials list --type proxmox

# Remove a credential
homelab-mcp credentials remove 192.168.1.10

La CLI proporciona CRUD completo sobre las credenciales: add (crear/actualizar — upsert), list (leer), remove (eliminar). No hay un subcomando update separado — volver a ejecutar add reemplaza tanto el secreto del llavero como el tipo de autenticación de la entrada del registro.

Las credenciales se almacenan en el llavero del sistema operativo (libsecret en Linux, Keychain en macOS). Cuando el llavero del SO no está disponible (servidores sin cabeza), las credenciales recurren a las variables de entorno.

Consulta la referencia de la CLI de credenciales para obtener la documentación completa.

Configuración del cliente MCP

Desde PyPI (uvx) — recomendado:

{
  "mcpServers": {
    "homelab": {
      "command": "uvx",
      "args": ["homelab-mcp"]
    }
  }
}

Desde clon de fuente:

{
  "mcpServers": {
    "homelab": {
      "command": "uv",
      "args": ["run", "python", "run_server.py"],
      "cwd": "/path/to/homelab_mcp"
    }
  }
}

Desarrollo

# Install with dev dependencies
uv sync --group dev

# Run tests (unit only, no Docker required)
uv run pytest tests/ -m "not integration"

# Code quality
uv run ruff check src/ tests/
uv run mypy src/

Consulta DEPLOYMENT.md para obtener detalles sobre el despliegue en producción.

Estructura del proyecto

src/homelab_mcp/
  server.py              # MCP server with JSON-RPC protocol
  tool_schemas/          # Tool definitions (8 schema files)
  tool_annotations.py    # MCP annotation hints per tool
  ssh_tools.py           # SSH discovery and hardware detection
  service_installer.py   # Service installation framework
  infrastructure_crud.py # Infrastructure lifecycle management
  vm_operations.py       # VM/container operations
  sitemap.py             # Network topology mapping
  database.py            # SQLite device tracking
  error_handling.py      # Centralized error handling
  credential_store.py    # OS keyring credential storage
  log_filter.py          # Credential redaction for log output
  prompt_registry.py     # MCP prompts registry
  resource_readers.py    # MCP resource read handlers
  service_templates/     # YAML service definitions
testsprite_tests/        # TestSprite generated test suite (hackathon)
tests/                   # Unit and integration tests
docs/                    # Full documentation

Agradecimientos

Integración de scripts de la comunidad de Proxmox impulsada por community-scripts/ProxmoxVE (Licencia MIT).

Contribución

  1. Haz un fork del repositorio

  2. Crea una rama de características

  3. Escribe pruebas para la nueva funcionalidad

  4. Asegúrate de que todas las pruebas pasen

  5. Envía una solicitud de extracción (pull request)

Licencia

Licencia MIT -- consulta el archivo LICENSE para más detalles.

Available Tools

58 tools
analyze_network_topologyB
Read-onlyIdempotent

Analyze the network topology and provide insights about the discovered devices

Inputs: no named parameters.

bulk_discover_and_mapA
Idempotent

Discover multiple devices via SSH and store them in the network site map database

Inputs: targets (required).

check_ansible_serviceB
Read-onlyIdempotent

Check the status of an Ansible-managed service deployment

Inputs: hostname (required), service_name (required), password, username.

check_service_requirementsA
Read-onlyIdempotent

Check if a device meets the requirements for a service installation

Inputs: hostname (required), service_name (required), password, username.

clone_proxmox_vmB

Clone a VM or container to create a new one

Inputs: node (required), vmid (required), new_vmid (required), full, +3 more.

control_vmB
Idempotent

Control VM state (start, stop, restart)

Inputs: action (required), vm_name (required), platform (required), device_id (required).

create_infrastructure_backupC

Create a backup of current infrastructure state

Inputs: device_ids, backup_name, backup_scope, include_data.

create_proxmox_lxcB

Create a new LXC container on Proxmox

Inputs: node (required), vmid (required), hostname (required), host, +10 more.

create_proxmox_vmB

Create a new VM (QEMU) on Proxmox

Inputs: host (required), name (required), node (required), vmid (required), +10 more.

decommission_deviceA
DestructiveIdempotent

Safely remove a device from the network infrastructure. Stops services, removes the device from clusters, optionally migrates services per migration_plan, then deletes the sitemap row. Use remove_device for inventory-only deletion of one row; use purge_devices for bulk filter-based inventory deletion; use decommission_device when host-side cleanup (stop services, remove from clusters) is required before deletion.

Inputs: device_id (required), dry_run, force_removal, validate_only, +1 more.

decommission_device_previewA
Read-onlyIdempotent

Preview what decommission_device would affect without executing. Returns a structured dry-run report. No infrastructure is modified.

Inputs: device_id (required), force_removal, validate_only, migration_plan.

delete_proxmox_vmB
DestructiveIdempotent

Delete a VM or container from Proxmox

Inputs: node (required), vmid (required), host, purge, +2 more.

delete_proxmox_vm_previewA
Read-onlyIdempotent

Preview what delete_proxmox_vm would affect without executing. Returns a structured dry-run report. No VM is deleted.

Inputs: node (required), vmid (required), host, purge, +1 more.

deploy_infrastructureB

Deploy new infrastructure based on AI recommendations or user specifications

Inputs: deployment_plan (required), validate_only.

deploy_vmB

Deploy a new VM/container on a specific device

Inputs: vm_name (required), platform (required), device_id (required), vm_config.

destroy_terraform_serviceA
DestructiveIdempotent

Destroy a Terraform-managed service and clean up all resources

Inputs: hostname (required), service_name (required), dry_run, password, +1 more.

destroy_terraform_service_previewA
Read-onlyIdempotent

Preview what destroy_terraform_service would affect without executing. Returns a structured dry-run report. No resources are destroyed.

Inputs: hostname (required), service_name (required), password, username.

discover_and_mapA
Idempotent

Discover a device via SSH and store it in the network site map database. Recommended follow-up: run the configure_host_fingerprint prompt to capture per-host capability signals for drift detection.

Inputs: hostname (required), port, key_path, username.

get_device_changesB
Read-onlyIdempotent

Get change history for a specific device

Inputs: device_id (required), limit.

get_network_sitemapA
Read-onlyIdempotent

Get all discovered devices from the network site map database

Inputs: no named parameters.

get_proxmox_node_statusA
Read-onlyIdempotent

Get detailed status of a Proxmox node (CPU, memory, uptime, etc.)

Inputs: node (required), host.

get_proxmox_script_infoA
Read-onlyIdempotent

Get detailed information about a specific Proxmox community script

Inputs: script_name (required), category.

get_proxmox_vm_statusB
Read-onlyIdempotent

Get status of a specific VM or container

Inputs: node (required), vmid (required), host, vm_type.

get_service_infoC
Read-onlyIdempotent

Get detailed information about a specific service

Inputs: service_name (required).

get_service_statusC
Read-onlyIdempotent

Get the current status of an installed service

Inputs: hostname (required), service_name (required), password, username.

get_vm_logsA
Read-onlyIdempotent

Get logs from a specific VM/container

Inputs: vm_name (required), platform (required), device_id (required), lines.

get_vm_statusA
Read-onlyIdempotent

Get detailed status of a specific VM

Inputs: vm_name (required), platform (required), device_id (required).

install_serviceC

Install a homelab service on a target device

Inputs: hostname (required), service_name (required), password, username, +1 more.

list_available_servicesA
Read-onlyIdempotent

List all available homelab services that can be installed

Inputs: no named parameters.

list_keyring_credentialsA
Read-onlyIdempotent

List hosts that have credentials stored in the OS keyring registry. Call this before ssh_discover or ssh_execute_command to check whether a host has stored credentials. Returns hostname and username per entry.

Inputs: credential_type.

list_proxmox_resourcesB
Read-onlyIdempotent

List all Proxmox cluster resources (VMs, containers, nodes, storage).

Inputs: host, resource_type.

list_registered_serversA
Read-onlyIdempotent

List all registered servers with their SSH credentials and connection status

Inputs: active_only.

list_vmsA
Read-onlyIdempotent

List all VMs/containers on a device

Inputs: device_id (required), platforms.

manage_proxmox_vmC
Idempotent

Manage a VM or container (start, stop, shutdown, reboot, reset, suspend, resume)

Inputs: node (required), vmid (required), action (required), host, +1 more.

plan_terraform_serviceA
Idempotent

Generate a Terraform plan to preview changes without applying them

Inputs: hostname (required), service_name (required), password, username, +1 more.

purge_devicesA
DestructiveIdempotent

Bulk-delete sitemap rows by filter. Single mutually-exclusive filter per call selected by filter_type. Supported filter_types: 'hostname' (exact-match string, no glob/LIKE), 'last_seen_older_than_days' (integer N — rows where last_seen < now - N days, exclusive boundary; N=0 matches all rows older than this instant), 'status' (exact match string like 'error' or 'success'), 'ip_range' (CIDR string like '192.168.1.0/24' or '2001:db8::/32' — rows whose connection_ip is not a valid IP are silently skipped). Composite/ANDed filters are NOT supported (use two calls). Pass dry_run=true to preview the candidate set without deleting. Zero-match returns success with purged_count=0, never an error. Note: filter_type='status', value='error' covers ONLY status='error' rows; use purge_failed_discoveries for the broader failed-discovery filter (includes zombie hostnames). Use remove_device for inventory-only deletion of one row; use purge_devices for bulk filter-based inventory deletion; use decommission_device when host-side cleanup (stop services, remove from clusters) is required before deletion.

Inputs: value (required), filter_type (required), dry_run.

purge_devices_previewA
Read-onlyIdempotent

Preview the result of purge_devices without persisting. Returns the candidate set the bulk delete would touch. Read-only — no DB write. Phase 44 D-11.

Inputs: value (required), filter_type (required).

purge_failed_discoveriesA
DestructiveIdempotent

Remove sitemap rows for devices where discovery failed (status='error' or empty/null/'unknown' hostname). Pass dry_run=true to preview the removal candidates without deleting them. (Equivalent to purge_devices with the failed-discovery filter — preserves the 4-clause OR semantics; bare purge_devices(filter_type='status', value='error') matches ONLY status='error' rows, NOT zombie hostnames.) Use remove_device for inventory-only deletion of one row; use purge_devices for bulk filter-based inventory deletion; use decommission_device when host-side cleanup (stop services, remove from clusters) is required before deletion.

Inputs: dry_run.

refresh_terraform_serviceB
Idempotent

Refresh Terraform state and detect configuration drift

Inputs: hostname (required), service_name (required), password, username.

register_serverA
Idempotent

Verify SSH connectivity to a registered server using keyring credentials. Does not write any credentials — credentials must already be stored via homelab-mcp credentials add <hostname> <username> in the CLI. Returns a status object with verified=true on successful handshake.

Inputs: hostname (required), username (required), port, display_name.

remove_deviceA
DestructiveIdempotent

Delete a single sitemap row by device_id. Pure SQL DELETE on the sitemap row plus cascade DELETE on discovery_history rows for that device_id. No SSH dial, no Ansible runs, no Terraform plans on the handler call path. The keyring credential entry bound via ssh_credential_id is preserved — only the sitemap row is dropped, so a subsequent discover_and_map can re-bind without re-adding the credential. Pass dry_run=true to preview the would-delete row payload without writing. Use remove_device for inventory-only deletion of one row; use purge_devices for bulk filter-based inventory deletion; use decommission_device when host-side cleanup (stop services, remove from clusters) is required before deletion.

Inputs: device_id (required), dry_run.

remove_device_previewA
Read-onlyIdempotent

Preview the result of remove_device without persisting. Returns the would-delete row payload. Read-only — no DB write, no keyring touch. Phase 44 D-11.

Inputs: device_id (required).

remove_vmC
DestructiveIdempotent

Remove a VM/container from a device

Inputs: vm_name (required), platform (required), device_id (required), force, +1 more.

remove_vm_previewA
Read-onlyIdempotent

Preview what remove_vm would affect without executing. Returns a structured dry-run report. No infrastructure is modified.

Inputs: vm_name (required), platform (required), device_id (required), force.

rollback_infrastructure_changesB
DestructiveIdempotent

Rollback recent infrastructure changes

Inputs: backup_id (required), dry_run, device_ids, validate_only, +1 more.

rollback_infrastructure_changes_previewA
Read-onlyIdempotent

Preview what rollback_infrastructure_changes would affect without executing. Returns a structured dry-run report. No infrastructure is modified.

Inputs: backup_id (required), device_ids, validate_only, rollback_scope.

run_ansible_playbookB

Run an existing Ansible playbook for a service

Inputs: hostname (required), service_name (required), tags, password, +3 more.

scale_servicesB

Scale services up or down based on resource analysis

Inputs: scaling_plan (required), validate_only.

scan_infrastructure_driftA
Read-onlyIdempotent

Scan for infrastructure drift against the sitemap. Returns a four-bucket coverage report — probed_ok (sitemap host probed successfully), unreachable (sitemap host that did not respond), unknown (reserved for Phase 39 — infrastructure present on a Proxmox hypervisor but absent from sitemap), and changed (reserved for Phase 39 — fingerprint differs from stored). All four buckets are always present in the response (empty arrays for Phase-39-reserved buckets) so client code can iterate without defensive checks. Each scan also returns a counts sub-dict mirroring bucket sizes and, when zero hosts were scanned (empty sitemap or filter narrowed to zero), a top-level guidance field pointing to the sitemap CRUD tools (discover_and_map, get_network_sitemap, purge_failed_discoveries, decommission_device). Recovery from credential-resolution failure is handled via 'homelab-mcp credentials add --type proxmox'.

Inputs: node, vm_type.

search_proxmox_scriptsA
Read-onlyIdempotent

Search Proxmox community installation scripts from the community-scripts/ProxmoxVE repository

Inputs: query (required), category, include_metadata.

ssh_discoverA
Read-onlyIdempotent

SSH into a system and gather hardware/system information. If credentials were stored with credentials add, username and password are auto-injected from the keyring — omit them. If authentication fails with 'No credentials found', run homelab-mcp credentials add <hostname> <username> in the terminal or call list_keyring_credentials to see what is already stored. Recommended follow-up after onboarding: run the configure_host_fingerprint prompt to capture per-host capability signals for drift detection.

Inputs: hostname (required), port, key_path, password, +1 more.

ssh_execute_commandA

Execute a command on a remote system via SSH. If credentials were stored with credentials add, username and password are auto-injected from the keyring — omit them. If authentication fails with 'No credentials found', run homelab-mcp credentials add <hostname> <username> in the terminal or call list_keyring_credentials to see what is already stored.

Inputs: command (required), hostname (required), port, sudo, +2 more.

start_interactive_shellA

Start an interactive web-based shell session on a remote system. Opens a browser-based terminal with full TTY support for running interactive commands and scripts. Perfect for Proxmox community scripts or any interactive command-line tools. Requires HTTP server mode (--http flag). In stdio mode, this tool returns an error with setup instructions.

Inputs: hostname (required), port, password, username, +1 more.

suggest_deploymentsB
Read-onlyIdempotent

Suggest optimal deployment locations based on current network topology and device capabilities

Inputs: no named parameters.

update_device_configA

Update configuration of an existing device

Inputs: device_id (required), config_changes (required), validate_only, backup_before_change.

update_device_fingerprintA
Idempotent

Merge fingerprint data (kernel, OS, package digest, capabilities) into a device's sitemap row. Top-level keys overwrite (last-write-wins). The capabilities sub-dict updates one level deep — each incoming top-level capability key REPLACES its stored entry entirely (NOT a recursive merge); stored capability keys not present in the call are preserved. Callers updating any field within a capability must pass the full capability dict. Run discover_and_map first to populate the device. See the configure_host_fingerprint prompt for the conversational workflow. Persists to DB and bumps updated_at; last_seen is preserved (Phase 38 REVIEW-FIX WR-03).

Inputs: hostname (required), fingerprint (required).

update_device_fingerprint_previewA
Read-onlyIdempotent

Preview the merge result of update_device_fingerprint without persisting. Returns the would-be merged fingerprint dict using the same merge rules: top-level overwrite + capabilities one-level overwrite (incoming capability keys replace stored entries entirely; not recursive). Read-only — no DB write, no last_seen or updated_at mutation. Phase 38 D-05c.

Inputs: hostname (required), fingerprint (required).

validate_infrastructure_changesA
Read-onlyIdempotent

Validate infrastructure changes before applying them

Inputs: change_plan (required), validation_level.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 58 tools

    Disambiguation3/5

    While most tools target distinct actions, the abundance of deletion/removal variants (remove_device, purge_devices, decommission_device, etc.) and overlapping VM management tools create ambiguity. Agents may struggle to differentiate between subtly different tools like decommission_device and purge_failed_discoveries.

    Naming Consistency4/5

    Tool names follow a consistent verb_noun pattern with snake_case (e.g., create_proxmox_vm, get_network_sitemap). Preview tools append '_preview' uniformly. Minor deviations like start_interactive_shell are clear but break the pattern slightly.

    Tool Count3/5

    At 58 tools, the count is high for a single server. The broad scope (network discovery, Proxmox, services, Terraform) justifies many tools, but some could be consolidated (e.g., multiple deletion methods). The set feels slightly heavy but not extreme.

    Completeness4/5

    The tool set covers major lifecycle stages (create, read, update, delete, preview) across multiple domains. Notable gaps include lack of a direct sitemap update tool and limited service management beyond installation. However, the presence of preview tools for dangerous operations strengthens completeness.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables management of homelab infrastructure, including Docker/Podman containers, Ollama AI models, Pi-hole DNS, Unifi networks, and Ansible inventory, with built-in security checks and automated pre-push validation.
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to manage Proxmox VE infrastructure, including VMs, containers, storage, and cluster operations via natural language.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that gives AI assistants real-time access to your homelab infrastructure. It enables querying node status, managing Docker containers, controlling Proxmox VMs, and inspecting OPNsense firewall state through natural conversation.
      51 PyPI
      2
      MIT