Skip to content

Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.

docs: MCP docs updated

Saurav Panda612defdab05b
diff --git a/docs/customize/mcp-server.mdx b/docs/customize/mcp-server.mdx
index 8ba693125..b08361d15 100644
--- a/docs/customize/mcp-server.mdx
+++ b/docs/customize/mcp-server.mdx
@@ -71,33 +71,28 @@ You can configure browser-use through environment variables:
The MCP server exposes these browser automation tools:
### Autonomous Agent Tools
-- **`run_browser_task`** - Run a complete browser automation task with an AI agent
-- **`run_browser_task_streaming`** - Same as above but with streaming responses
+- **`retry_with_browser_use_agent`** - Run a complete browser automation task with an AI agent (use as last resort when direct control fails)
### Direct Browser Control
- **`browser_navigate`** - Navigate to a URL
- **`browser_click`** - Click on an element by index
- **`browser_type`** - Type text into an element
-- **`browser_get_state`** - Get current page state and screenshot
+- **`browser_get_state`** - Get current page state and interactive elements
- **`browser_scroll`** - Scroll the page
- **`browser_go_back`** - Go back in browser history
-- **`browser_go_forward`** - Go forward in browser history
-- **`browser_refresh`** - Refresh the current page
### Tab Management
- **`browser_list_tabs`** - List all open browser tabs
- **`browser_switch_tab`** - Switch to a specific tab
- **`browser_close_tab`** - Close a tab
-- **`browser_new_tab`** - Open a new tab
### Content Extraction
- **`browser_extract_content`** - Extract structured content from the current page
-- **`browser_take_screenshot`** - Take a screenshot of the current page
-### File Operations
-- **`read_file`** - Read content from a file
-- **`write_file`** - Write content to a file
-- **`list_files`** - List files in a directory
+### Session Management
+- **`browser_list_sessions`** - List all active browser sessions with details
+- **`browser_close_session`** - Close a specific browser session by ID
+- **`browser_close_all`** - Close all active browser sessions
## Example Usage
@@ -140,12 +135,12 @@ async def use_browser_mcp():
)
print(result.content[0].text)
- # Take a screenshot
+ # Get page state
result = await session.call_tool(
- "browser_take_screenshot",
- arguments={}
+ "browser_get_state",
+ arguments={"include_screenshot": True}
)
- print("Screenshot taken!")
+ print("Page state retrieved!")
asyncio.run(use_browser_mcp())
```