Connect your account, then chat with AI to run tools.
Automate a local Chrome browser with Playwright: navigate, click, type, inspect pages, capture screenshots, and debug localhost apps from chat.
Try this workflow
Debug a localhost page
Open http://localhost:3000, inspect the visible page, capture console errors and network failures, then summarize what is blocking the UI.
Opens MCPBundles Studio with this server selected. After sign-in, chat and run tools from the same thread.
Browse all toolsBuilt for
Frontend Developers, QA Engineers, Localhost Debugging, Product Operations
Debug a localhost page
Uses local browser access for dev-server debugging.
Open http://localhost:3000, inspect the visible page, capture console errors and network failures, then summarize what is blocking the UI.
Run a form flow
Combines snapshots, clicks, typing, and visible text review.
Navigate through the signup flow, fill the form fields with test data, and report any validation or layout issues before submitting.
Capture visual evidence
Uses screenshots for visual QA and page review.
Load the dashboard page, take a screenshot, and describe what is visible above the fold on desktop.
Inspect performance signals
Turns browser diagnostics into actionable frontend notes.
Open this page, emulate a slower device, capture network requests and console messages, then summarize performance risks.
What is Local Browser best for?
It is best for browser automation against sites reachable from the user's machine, especially localhost development servers, internal apps, and interactive UI debugging.
How does Local Browser differ from Remote Browser?
Local Browser runs Chrome on the user's machine through the desktop proxy, so it can reach localhost directly. Remote Browser runs Chrome in the cloud.
Can agents see screenshots?
Yes. Screenshot tools return visual content that agents can inspect, which is useful for layout review, visual QA, and debugging UI states.
Domain knowledge for Local Browser — workflow patterns, data models, and gotchas for your AI agent.
Chrome runs on the user's machine and is controlled through the MCPBundles Desktop proxy CDP tunnel. The browser resolves localhost on that same machine — ideal for dev-server QA, interactive debugging, and visual verification.
Cinematic tour (recommended):
Raw screencast: browser_start_recording → navigate → browser_wait_for while still recording → browser_stop_recording → export hero_from_capture or product_hunt_kit.
Studio streaming (screencast): browser_start_recording → navigate /studio?q=…&autosend=1 → browser_wait_studio_stream (waits for tool spinners / Executing… to clear) → browser_stop_recording. Do not wait for the full reply before starting recording. browser_wait_for time is in seconds (never timeout=12000). Checked-in flow: browser_run_journey with journey=studio-autosend-screencast.
Open a page — resize viewport, then navigate. Success means the navigate response includes URL, title, and HTTP 200.
Sign in then continue — navigate to the app's login URL with callbackUrl set to the post-auth destination. Prefer browser_fill_form with CSS selector refs, or click/type each field with snapshot refs. Redirects can take 1–3 seconds; re-read location from JavaScript evaluation or from the snapshot's URL field.
Review UI quality — after navigate: browser_ux_review for a structured report with clustered ui_findings, optional visual_findings, and a limits block (layout, accessibility, console, form, copy). Set visualCritique=true for PydanticAI vision observations; use captureFrames (desktop, mobile, desktop_scroll_end, mobile_menu_open) for richer shots. Or call browser_responsive_capture, browser_accessibility_audit, and browser_layout_probe individually. Use snapshot with boxes=true or screenshots when you need pixels.
Run an axe-core accessibility audit on the current browser page. Returns structured WCAG violations with selectors and HTML snippets.
Perform click on a web page
Click a link that opens in a new tab and switch to it. Use for links with target=_blank or Ctrl+click to force new tab.
Close the current page or the entire browser session. Use to release resources when done with browser automation.
Returns console messages. Note: Only messages logged AFTER browser session started are available.
Perform drag and drop between two elements
Emulate network conditions and CPU throttling to test performance on slow connections or devices
Evaluate JavaScript expression on page or element
Upload files to a file input or upload button using base64-encoded file payloads.
Fill multiple form fields
Get detailed information about a captured console message including structured arguments, stack trace, and source location.
Get browser cookies including HttpOnly cookies. Returns name, value, domain, path, expires, httpOnly, secure, and sameSite for each cookie. Useful for...
Get detailed information about a captured network request: status, response headers, timing, and a truncated text body when available.
Poll a browser capture asset until S3 flush completes. When status is ready, use asset_id in marketing project timeline and hero_from_capture export.
Read localStorage or sessionStorage from the current page. Returns all key-value pairs or a specific key. Useful for extracting auth tokens, user pref...
Get the visible text content of the current page. Lighter than browser_snapshot when you only need text. Hidden elements (display:none, visibility:hid...
Handle a dialog
Hover over element on page
Click an element inside an iframe. Use browser_snapshot to get iframeRef and element ref.
Fill an input field inside an iframe. Use browser_snapshot to get iframeRef and field ref.
Install the browser specified in configuration (chromium, firefox, or webkit). Downloads and sets up the browser if not already installed. This is typ...
Analyze page layout at desktop (1440x900) and mobile (390x844) for horizontal overflow, clipped URLs/slugs in narrow copy rows, narrow readable column...
Navigate to a URL in the browser. Returns navigation result with final URL (after redirects), page title, and status. Use this as the starting point f...
Go back to the previous page
Returns network requests for the current page with request IDs for detailed inspection
Start or stop performance tracing to analyze page performance, Core Web Vitals (LCP, FID, CLS), and identify bottlenecks
Press a key or key combination on the keyboard. Supports special keys (Enter, Escape, Tab) and modifiers (Control, Shift, Alt, Meta). Optionally focus...
Record a short screencast on the current Local Browser tab via CDP (start → wait → stop in one call). Returns asset_id; poll browser_get_recording_sta...
Resize the browser window
Resize to desktop (1440x900) and mobile (390x844), run a layout probe at each size, and optionally capture screenshots. By default returns compact met...
Run a Playwright Python code snippet. The code receives 'page' (Playwright Page object) and can perform any page interaction. Use 'return' to return a...
Run a checked-in Browser Media journey (YAML under app/tools/browser/journeys). Dispatches browser_* steps in order; returns per-step results. Pair wi...
Save the current page as a PDF file. Returns base64-encoded PDF if path not provided.
Scroll the page by direction/amount, scroll to top/bottom, or scroll a specific element into view. Essential for lazy-loading pages and content below ...
Select an option in a dropdown
Set or delete browser cookies including HttpOnly cookies. Use 'cookies' to add/update cookies (name+value required, domain defaults to current page). ...
Capture one crisp keyframe of the current page as a film beat, with an optional caption. Call once per scene (navigate/scroll, then snap). Finish with...
Capture accessibility snapshot of the current page, this is better than screenshot
Start screen recording on the active Local Browser tab via CDP screencast. Navigate and interact, then call browser_stop_recording to upload frames to...
Stop the active browser screencast and enqueue upload of JPEG frames to S3. Returns asset_id immediately; poll browser_get_recording_status until read...
List, create, close, or select a browser tab.
Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.
Type text into editable element
Review the current page for UX issues: responsive layout defects, WCAG accessibility violations, console errors, form label gaps, and copy leaks. Retu...
Wait for text to appear or disappear or a specified time to pass
While Local Browser is recording, wait for MCPBundles Studio autosend to finish (tool-call spinners and 'Executing...' clear, assistant reply present)...
Playwright MCP server — local Chrome browser running on your machine via MCPBundles Desktop. Full browser automation: navigate, click, type, screenshot, fill forms, run JavaScript, inspect network/console, and performance profiling with direct localhost access. It provides 46 tools that AI agents can use through the Model Context Protocol (MCP).
Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/browser. Authentication is handled automatically.
Local Browser provides 46 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.
Local Browser uses API Key. Local Browser requires credentials. Connect via MCPBundles and authentication is handled automatically.
It is best for browser automation against sites reachable from the user's machine, especially localhost development servers, internal apps, and interactive UI debugging.
Local Browser runs Chrome on the user's machine through the desktop proxy, so it can reach localhost directly. Remote Browser runs Chrome in the cloud.
Yes. Screenshot tools return visual content that agents can inspect, which is useful for layout review, visual QA, and debugging UI states.
Use the accessibility snapshot to find element references, then click, type, or fill through those references instead of relying on raw selectors.
Connect Local Browser to any MCP client in minutes
https://mcp.mcpbundles.com/bundle/browserThe link prefills the Add custom connector dialog — you still review the values and click Add, then Connect to complete OAuth.
Local Browser and paste the MCP URL into Remote MCP server URL.Custom connectors at claude.ai require a paid Claude plan (Pro, Max, Team, or Enterprise).
More developer tools integrations you might like
Split_io provides a feature flagging and experimentation platform, enabling developers to implement ...
Analyze CIDR networks, calculate subnet details, and check IP membership. Supports IPv4 and IPv6. Pu...
The Recreation API provides access to information about recreational areas, facilities, and activiti...
UpPromote is an affiliate management software that provides a platform for businesses to create, man...
Aviationstack is an API service that provides real-time and historical flight data, including flight...
Use the Ticketmaster Commerce API to look up available offers and products on various Ticketmaster p...