---
title: "LangChain MCP integration · mobilerun"
description: "Connect LangChain and LangGraph agents to real Android and iOS phones through the mobilerun hosted MCP server. Tested Python snippet, 33 tools."
url: "https://mobilerun.ai/integrations/langchain/"
---

# LangChain integration (via MCP)

Connect a LangChain or LangGraph agent to the mobilerun MCP server with a few lines of Python. It gets 33 tools to run tasks on real Android and iOS phones.

No extra package: langchain-mcp-adapters connects to the hosted MCP server directly.

## Before you start

- A mobilerun API key from [cloud.mobilerun.ai](https://cloud.mobilerun.ai/api-keys). It starts with `dr_sk_`.
- Python 3.10 or newer.
- An API key for the model that drives your agent. The example uses OpenAI; any chat model with tool calling works.
- A phone in your mobilerun account to run tasks on. Connecting and listing tools works without one.

## 1. Install and set your keys

terminal:

```bash
pip install langchain-mcp-adapters langchain langchain-openai
export MOBILERUN_CLOUD_API_KEY=dr_sk_YOUR_API_KEY
export OPENAI_API_KEY=YOUR_OPENAI_API_KEY
```

## 2. Connect and build the agent

The client opens a Streamable HTTP connection with your key as a Bearer token and turns every MCP tool into a LangChain tool.

agent.py:

```python
import asyncio
import os

from langchain.agents import create_agent
from langchain_mcp_adapters.client import MultiServerMCPClient

API_KEY = os.environ["MOBILERUN_CLOUD_API_KEY"]

client = MultiServerMCPClient(
    {
        "mobilerun": {
            "transport": "streamable_http",
            "url": "https://api.mobilerun.ai/v1/mcp",
            "headers": {"Authorization": f"Bearer {API_KEY}"},
        }
    }
)


async def main():
    tools = await client.get_tools()
    print(f"{len(tools)} tools:", ", ".join(t.name for t in tools))

    # Any tool-calling chat model works. This one needs OPENAI_API_KEY.
    agent = create_agent("openai:gpt-5.4", tools)
    question = "List my mobilerun devices and say which are ready."
    result = await agent.ainvoke(
        {"messages": [{"role": "user", "content": question}]}
    )
    print(result["messages"][-1].content)


asyncio.run(main())
```

Run `python agent.py`. It prints the tool names, then the agent's answer. `create_agent` returns a LangGraph graph, so the same agent also works as a node in a larger LangGraph workflow. It replaces `create_react_agent`, which LangGraph 1.x marks as deprecated.

## 3. Give it only the tools it needs

Some tools change a phone: reset it, remove apps, or start tasks that use credits. For a first agent, pass a short list: tasks, screenshots and device lookups.

agent.py · inside main():

```python
STARTER_TOOLS = {
    "list_devices", "get_device", "get_device_screenshot", "run_task",
    "get_task", "list_tasks", "stop_task", "get_task_media",
}

tools = [t for t in await client.get_tools() if t.name in STARTER_TOOLS]
agent = create_agent("openai:gpt-5.4", tools)
```

Tested 25 Sep 2026 against the live server with Python 3.12, langchain 1.4.2, langchain-mcp-adapters 0.3.2 and langgraph 1.2.12: connected, listed 33 tools, built the agent.

## What your agent can do

33 tools on the hosted server. Your model decides which tool to call. Tasks it starts run on mobilerun's own mobile agent and use credits and device minutes from your plan.

- **Run agent tasks**: Start a task in plain language on a phone, follow its status and steps, send it a message while it runs, or stop it. mobilerun's mobile agent does the tapping and typing. (run_task, get_task, list_tasks, send_task_message, stop_task, get_task_media)
- **See and drive the screen**: Take a screenshot, read the on-screen UI as structured text, and tap, swipe or type yourself when you want exact control. (get_device_screenshot, get_device_ui_state, device_action)
- **Manage phones**: List your phones, wait until one is ready, reboot or reset it, set its language, timezone and location, and apply saved profiles. (list_devices, get_device, manage_device, configure_device, profiles)
- **Apps and files**: Install, start, stop and remove apps, upload your own APKs, and move files on and off the phone. (list_apps_on_device, manage_device_apps, apps, manage_device_files)
- **Logins**: Keep app logins in the credentials vault and let tasks use them. Stored values are never sent back to the agent. (list_credentials, list_credential_packages, manage_credentials)
- **Network and eSIM**: Route a phone through mobilerun Connect residential IPs or your own SOCKS5 or WireGuard proxy, and manage eSIM profiles. (connect, proxies, manage_esim)
- **Workflows and webhooks**: Turn a task into a workflow with a schedule or event trigger, send results to your own webhook endpoints, and look up timezones and app events. (create_flow, create_trigger, create_action, manage_flow, list_workflow_resources, get_workflow_resource, workflow_events, webhooks, platform_catalog)

## Notes

**Which transport does the server use?** Streamable HTTP at `https://api.mobilerun.ai/v1/mcp`. The server is stateless and answers POST requests only, so a client set to SSE gets a 405. Choose streamable HTTP in your client.

**Where does the API key go?** In an `Authorization: Bearer dr_sk_...` header. Read it from an environment variable on your server, and keep it out of code you commit or ship to a browser.

**What does it cost?** Tasks your agent starts use credits, and phones that are on use device minutes, the same as calls to the REST API. The model that drives your agent is billed by its own provider. See [pricing](https://mobilerun.ai/pricing/).

**Can I sign in with OAuth instead of a key?** The API key setup on this page is the one we tested. Interactive clients such as Claude Desktop can use OAuth, see the [MCP page](https://mobilerun.ai/mcp/).

LangChain MCP docs: https://docs.langchain.com/oss/python/langchain/mcp
Get an API key: https://cloud.mobilerun.ai/api-keys

---

Source: https://mobilerun.ai/integrations/langchain/