home / mcp / browser mcp server
Provides a local MCP browser debugger for frontend inspection, DOM analysis, and network/log monitoring.
Configuration
View docs{
"mcpServers": {
"emmanuelbarbosamonteiro-mcp-server-browser": {
"command": "node",
"args": [
"c:\\Users\\Emmanuel\\Desktop\\mcp\\mcp-browser\\dist\\index.js"
]
}
}
}You can use the MCP Browser Debugger to inspect and debug frontend pages end-to-end. It lets you open a visible browser, log in to a site, navigate pages, inspect the DOM, run JavaScript in the page context, capture network activity and console logs, and take screenshots—all through a programmable MCP server you control from your client.
To get started, first ensure the browser is open. Then perform a visible browser session, log in if needed, and proceed with inspection and debugging tasks such as viewing the DOM, running scripts, or monitoring network activity.
Install prerequisites and set up the MCP Browser Debugger locally.
1. Install dependencies and build the TypeScript project.
npm install
npm run buildConfigure your MCP client to connect to the browser debugger as a local stdio server. The following configuration uses Node to run the built browser debugger from a local path.
{
"mcpServers": {
"browser_debugger": {
"command": "node",
"args": ["c:\\Users\\Emmanuel\\Desktop\\mcp\\mcp-browser\\dist\\index.js"]
}
}
}- The browser runs in a mode that is suitable for debugging, with session data kept in memory during a session. - Sessions, cookies, and localStorage are cleared when the browser is closed per user instruction. - Logs and network activity accumulate between navigations; you can clear them when needed.
- Always verify the browser status before opening a new instance to avoid losing an active login session. - Build the project after any code changes before restarting the MCP client variant. - Use the provided command flow to ensure you maintain a single login session throughout debugging.
Opens the browser in visible mode to show actions in real time.
Closes the browser and ends the session, clearing cookies and storage.
Performs automated login to a specified URL and keeps the session active for inspection.
Navigates to a given URL with timeout and wait conditions.
Extracts the complete HTML of the current DOM.
Inspects a specific element and returns computed styles and attributes.
Finds multiple elements using a CSS selector and returns matches.
Evaluates an XPath expression against the current document.
Extracts the full page source including scripts and styles.
Executes arbitrary JavaScript in the page context and returns the result.
Retrieves console logs accumulated during the session.
Monitors network activity and returns HTTP requests and responses.
Captures a screenshot of the full page or a specific element.
Clicks on a specified element and optionally waits for navigation.
Types text into an input field, with optional clear before typing.
Reads localStorage entries from the page.
Lists cookies stored for the current page.
Returns general information about the current page.
Returns general information about the current page.
Returns general information about the current page.
Evaluates an XPath expression against the current document.