Icemoon — control a real iPhone with AI vs How Persistence Works

A side-by-side look at the Icemoon — control a real iPhone with AI and How Persistence Works MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Icemoon — control a real iPhone with AI logoIcemoon — control a real iPhone with AIOS Automation · Local subprocess (stdio)Control real, physical iPhones with AI: screen reading, human-like touch, no jailbreak.40FairAuth: not declaredHow Persistence Works logoHow Persistence WorksOS AutomationVisual Desktop Bridge - Give any AI full control over Windows to automate apps and inputs.23EmergingAuth: not declared

Verdict: choose Icemoon — control a real iPhone with AI for os automation work as a local process; choose How Persistence Works for os automation. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Icemoon — control a real iPhone with AI logoChoose Icemoon — control a real iPhone with AI when

  • You need dedicated capabilities in the OS Automation domain.
  • You prefer a local stdio subprocess transport.
Explore Icemoon — control a real iPhone with AI

How Persistence Works logoChoose How Persistence Works when

  • You need dedicated capabilities in the OS Automation domain.
Explore How Persistence Works

Feature & specification comparison

Rows where the two servers differ are marked.

SpecIcemoon — control a real iPhone with AI logoIcemoon — control a real iPhone with AIHow Persistence Works logoHow Persistence Works
CategoryOS AutomationOS Automation
Quality signal40/100 · Fair23/100 · Emerging
Install commandConfirmedNot confirmed yet
TransportLocal subprocess (stdio)—
AuthNot declaredNot declared
PricingNot declaredNot declared
Required env varsNone listedNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars06
Directory activity 3 views 0 installs 0 upvotes 2 views 0 installs 0 upvotes
ToolsNot listedNot listed

Tools & capabilities

Icemoon — control a real iPhone with AI tools

No tool names declared yet. Check the project README from the listing page.

How Persistence Works tools

No tool names declared yet. Check the project README from 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.

Icemoon — control a real iPhone with AI

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "icemoon-control-a-real-iphone-with-ai": {
      "command": "npx",
      "args": [
        "-y",
        "icemoon-mcp"
      ]
    }
  }
}

How Persistence Works

No confirmed install command for How Persistence Works yet — follow the setup steps linked from its listing page rather than a guessed package name.

Frequently asked questions

Icemoon — control a real iPhone with AI is categorized under OS Automation and uses a local stdio subprocess. How Persistence Works belongs to OS Automation and uses an install path we have not confirmed yet. Pick Icemoon — control a real iPhone with AI for os automation work and How Persistence Works for os automation.

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. How Persistence Works has no confirmed install command yet — follow its own setup instructions.

Icemoon — control a real iPhone with AI has no declared pricing — check the project's own site. How Persistence Works 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 icemoon-control-a-real-iphone-with-ai and bridge-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Icemoon — control a real iPhone with AI has a quality signal of 40/100 (Fair) with 3 views, 0 installs and 0 GitHub stars. How Persistence Works has 23/100 (Emerging) with 2 views, 0 installs and 6 GitHub stars.