Browser tools for LangChain agents.

1. Install Browz and open it

   Download Browz on the computer that runs your agent.

2. Install the packages

   The adapters, LangGraph’s prebuilt agent and a model provider.

   Terminalpip install langchain-mcp-adapters langgraph "langchain[openai]"

3. Load the tools and run

   MultiServerMCPClient starts the server inside Browz over stdio and turns its tools into LangChain tools. Set OPENAI_API_KEY first, or use another model.

   agent.pyimport asyncio from langchain_mcp_adapters.client import MultiServerMCPClient from langgraph.prebuilt import create_react_agent async def main(): client = MultiServerMCPClient({"browz": {"transport": "stdio", "command": "/Applications/Browz.app/Contents/Resources/browz-mcp", "args": []}}) agent = create_react_agent("openai:gpt-5", await client.get_tools()) out = await agent.ainvoke({"messages": [("user", "Using Browz: create a new profile called agent-check, start it, open https://example.com, tell me the page title, take a screenshot, then stop the session and delete the profile.")]}) print(out["messages"][-1].content) asyncio.run(main())

4. From a hosted agent (beta)

   The same client over HTTP, with an agent token read from BROWZ_AGENT_TOKEN.

   Pythonimport os from langchain_mcp_adapters.client import MultiServerMCPClient client = MultiServerMCPClient({"browz": {"transport": "http", "url": "https://mcp.gobrowz.com/mcp", "headers": {"Authorization": "Bearer " + os.environ["BROWZ_AGENT_TOKEN"]}}}) tools = await client.get_tools() # inside an async function

Client API from LangChain MCP docs, langchain-mcp-adapters.

• The example uses the macOS path of the server; in your own code, read it from the BROWZ_MCP environment variable or use npx -y @browz/mcp so it runs on every computer.
• The remote server at https://mcp.gobrowz.com/mcp is in free public beta: it needs the Browz app open with Remote control on, on a computer with a hardware security chip, and offers the profile, tab and page tools. See what it needs and what it offers.
• Browz has to be installed and open on the same computer: the local MCP server drives the app’s own profiles through its local API, and reads the app’s credentials itself, so no token goes in the config.
• A person completes sign-ins, 2FA codes and CAPTCHAs. The agent can pause with browz_request_human and hand you the profile’s window, then carry on in the same session. Browz never solves or bypasses CAPTCHAs.
• Use agents only where each site’s terms allow automated use, on accounts you are entitled to use. Our acceptable use policy applies to agents the same as to people.
• The MCP server is on every plan, Free included (5 profiles). How many agent sessions can be open at once depends on the plan: see pricing.