Vuda (visual Ui Debug Agent)

Created By
samihalawaa year ago
Overview

what is VUDA?

VUDA (Visual UI Debug Agent) is an autonomous debugging agent designed to empower AI models to visually analyze, test, and debug web interfaces using Playwright. It enables AI models to inspect web pages, identify UI bugs, test user workflows, and validate application performance without human intervention.

how to use VUDA?

To use VUDA, you can install it via an MCP-compatible gateway, use a quick installation script, or install it globally via npm or Docker. After installation, you can start the server and utilize various tools for visual analysis and debugging.

key features of VUDA?

  • Comprehensive visual analysis of web applications
  • Detection of UI issues by inspecting visual elements
  • Automatic testing of user workflows
  • Validation of API endpoints and backend responses
  • Monitoring of console logs for errors
  • Performance metrics analysis
  • Generation of detailed reports with recommendations

use cases of VUDA?

  1. Performing visual regression testing to catch UI changes.
  2. Validating end-to-end user flows in web applications.
  3. Monitoring application performance and identifying bottlenecks.

FAQ from VUDA?

  • Can VUDA work with any AI model?

Yes! VUDA can integrate with any AI model, even those without built-in vision capabilities.

  • Is VUDA easy to install?

Yes! VUDA can be installed using various methods including npm, Docker, and MCP gateways.

  • What platforms does VUDA support?

VUDA supports all major platforms including macOS, Linux, and Windows.

Server Config

{
  "mcpServers": {
    "github": {
      "name": "VUDA (Visual UI Debug Agent)",
      "url": "https://github.com/samihalawa/visual-ui-debug-agent-mcp",
      "innovation": true,
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GITHUB_PERSONAL_ACCESS_TOKEN=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",
        "samihalawa/visual-ui-debug-agent-mcp"
      ],
      "env": {
        "GITHUB_PERSONAL_ACCESS_TOKEN": "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"
      }
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
samihalawa
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago