Homebutler vs Stackpulse

A side-by-side look at the Homebutler and Stackpulse MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Homebutler logoHomebutlerMonitoring · Local subprocess (stdio)All-in-one homelab management MCP server. Monitor system resources, manage Docker containers, Wake-on-LAN, scan networks, check open ports, and run alerts — across multiple servers via SSH. Single 10MB binary, zero dependencies.71GreatAuth: no auth required
S
StackpulseMonitoring · Remote HTTP/SSE
8,900+ services' status, and your Stackpulse dashboards and URL monitors. Needs Pro.51GoodAuth: not declared

Verdict: choose Homebutler for monitoring work as a local process; choose Stackpulse for monitoring over a hosted endpoint. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Homebutler logoChoose Homebutler when

  • You need dedicated capabilities in the Monitoring domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: No auth required.
  • You want tools like proxmox_status, proxmox_guests, proxmox_node.
Explore Homebutler

S
Choose Stackpulse when

  • You need dedicated capabilities in the Monitoring domain.
  • You prefer a remote HTTP/SSE transport.
  • You want tools like search_services, get_service, list_outages.
Explore Stackpulse

Feature & specification comparison

Rows where the two servers differ are marked.

SpecHomebutler logoHomebutler
S
Stackpulse
CategoryMonitoringMonitoring
Quality signal71/100 · Great51/100 · Good
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Remote HTTP/SSE
AuthNo auth requiredNot declared
PricingFreeNot declared
Required env varsNone listedNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars304—
Directory activity 4 views 0 installs 0 upvotes 1 views 0 installs 0 upvotes
Tools4016

Tools & capabilities

Homebutler tools 40

  • proxmox_statusGet Proxmox VE version, cluster status, and resources
  • proxmox_guestsList Proxmox QEMU and LXC guests, optionally filtered by node, status, or type
  • proxmox_nodeGet detailed Proxmox node status
  • proxmox_tasksGet the 50 most recent Proxmox tasks for a node
  • system_statusGet system status including CPU, memory, disk usage, and uptime
  • proxmox_guest_startStart one explicitly targeted Proxmox guest after confirmation and return the accepted task UPID
  • proxmox_guest_rebootReboot one explicitly targeted Proxmox guest after confirmation and return the accepted task UPID
  • proxmox_guest_shutdownGracefully shut down one explicitly targeted Proxmox guest after confirmation and return the accepted task UPID
  • proxmox_task_statusInspect one asynchronous Proxmox task by node and opaque UPID
  • proxmox_script_listList the curated Proxmox VE Community Scripts catalog (community-scripts/ProxmoxVE)
  • proxmox_script_commandRender the pinned install command for one Proxmox VE Community Script. Never fetches or runs it; the caller reviews and runs it themselves on the Proxmox host
  • docker_listList Docker containers with their status, image, and ports
  • +28 more on the listing page

Stackpulse tools 16

  • search_servicesFinds services in the catalog of 9,700+ status pages by name, with their status now. Use it to find a service’s slug.
  • get_serviceOne service’s status from its official status page: what’s wrong, the components with a problem, 90 days of history and recent incidents.
  • list_outagesServices reporting a problem right now, the newest first: the 25 best-known, unless all is true or a limit is given.
  • list_dashboardsThe account’s dashboards (the ones this connection can see), with how many services and URL monitors each has and its worst status now.
  • get_stack_statusWhat’s going on now on a dashboard: a summary, then every service and URL monitor with a problem, with when the problem began and when its current status did. A URL monitor that’s down lists what started around then. Without a dashboard, every dashboard.
  • get_incident_historyIncidents on a dashboard in a window: the ones that started in it (with what else started at the same time) and the ones already going on. As far back as the plan’s history goes.
  • get_monitorOne of the account’s URL monitors: its status, its uptime over the last 30 days (or since it started) with the failed checks apart, response times, its certificate and its latest checks.
  • get_reliabilityHow reliable a dashboard’s services and URL monitors were over 7, 30 or 90 days: the least reliable first, with the share of time without a reported problem (minor issues count, so one long minor issue makes it low), time in each severity, incidents and recovery, and what tends to break together.
  • create_dashboardMakes a dashboard with a name and, optionally, services by slug (search_services finds them), within the plan’s dashboards and services. Answers with its address.
  • rename_dashboardRenames a dashboard. Its status page shares the name.
  • add_servicesAdds services to a dashboard by slug (search_services finds them), within the plan’s limit.
  • remove_servicesTakes services off a dashboard. Their history stays; adding one back shows it again.
  • +4 more on the listing page

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Homebutler

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "higangssh-homebutler": {
      "command": "npx",
      "args": [
        "-y",
        "homebutler@latest"
      ]
    }
  }
}

Stackpulse

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "stackpulse": {
      "url": "https://stackpulse.app/mcp"
    }
  }
}

Frequently asked questions

Homebutler is categorized under Monitoring and uses a local stdio subprocess. Stackpulse belongs to Monitoring and uses a remote HTTP/SSE transport. Pick Homebutler for monitoring work and Stackpulse for monitoring.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

Homebutler is listed as free. Auth: no auth required. Stackpulse has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add higangssh-homebutler and stackpulse as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Homebutler has a quality signal of 71/100 (Great) with 4 views, 0 installs and 304 GitHub stars. Stackpulse has 51/100 (Good) with 1 views, 0 installs and 0 GitHub stars.