┌──────────────────────────────────────────────────┐
│  Any AI Agent                                    │
│                                                  │
│  Claude ──── MCP (stdio) ──┐                     │
│  Codex ──── MCP (stdio) ───┤                     │
│                            ▼                     │
│                     ┌──────────────┐             │
│                     │  MCP Server  │             │
│                     │  mcp_server  │             │
│                     └──────┬───────┘             │
│                            │                     │
│  GPT ──── HTTP ────┐       │                     │
│  Gemini ── HTTP ───┤       │                     │
│  Custom ── HTTP ───┤       │                     │
│                    ▼       ▼                     │
│              ┌─────────────────┐                 │
│              │  phone_control  │                 │
│              │  (core package) │                 │
│              └────────┬────────┘                 │
│                       │                          │
│              ADB  ────┤──── Appium (optional)    │
│                       │                          │
├───────────────────────┼──────────────────────────┤
│  Android Emulator     │                          │
└───────────────────────┴──────────────────────────┘

git clone https://github.com/Ctrl-Creeper/phone-mcp-server.git
cd phone-mcp-server
pip install .

# With Appium support
pip install ".[appium]"

{
  "mcpServers": {
    "phone-control": {
      "command": "python",
      "args": ["/path/to/phone-mcp-server/mcp_server.py"]
    }
  }
}

claude mcp add phone-control python /path/to/phone-mcp-server/mcp_server.py

codex --mcp-config codex-mcp.json

{
  "mcpServers": {
    "phone-control": {
      "command": "python",
      "args": ["/path/to/phone-mcp-server/mcp_server.py"]
    }
  }
}

python http_server.py

import requests, openai

tools = requests.get("http://localhost:8080/openai/tools").json()

response = openai.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Open Settings on the phone"}],
    tools=tools,
)

tool_call = response.choices[0].message.tool_calls[0]
result = requests.post("http://localhost:8080/openai/call", json={
    "name": tool_call.function.name,
    "arguments": tool_call.function.arguments,
}).json()

import requests, google.generativeai as genai

tools_schema = requests.get("http://localhost:8080/openai/tools").json()

# Convert to Gemini format
gemini_tools = []
for t in tools_schema:
    f = t["function"]
    gemini_tools.append(genai.types.Tool(
        function_declarations=[genai.types.FunctionDeclaration(
            name=f["name"],
            description=f["description"],
            parameters=f["parameters"],
        )]
    ))

model = genai.GenerativeModel("gemini-2.0-flash", tools=gemini_tools)
chat = model.start_chat()
response = chat.send_message("Open the camera app")

# Execute the function call
fc = response.candidates[0].content.parts[0].function_call
result = requests.post("http://localhost:8080/openai/call", json={
    "name": fc.name,
    "arguments": dict(fc.args),
}).json()

import requests
from langchain_core.tools import StructuredTool

def phone_action(action: str, **kwargs):
    return requests.post(f"http://localhost:8080/phone/{action}", json=kwargs).json()

# Or dynamically load from schema
tools_schema = requests.get("http://localhost:8080/openai/tools").json()

# Capture UI hierarchy
curl -s localhost:8080/phone/capture -d '{"mode":"hierarchy"}' | jq .

# Tap element #3
curl -s localhost:8080/phone/tap -d '{"element":3}' | jq .

# Type text
curl -s localhost:8080/phone/type -d '{"text":"hello world"}' | jq .

# Get device info
curl -s -X POST localhost:8080/phone/device_info | jq .

# Fetch OpenAI tool schema
curl -s localhost:8080/openai/tools | jq .