https://github.com/debugg-ai/debugg-ai-mcp
Zero-Config, Fully AI-Managed End-to-End Testing for all code gen platforms.
https://github.com/debugg-ai/debugg-ai-mcp
automation browser end-to-end-testing web
Last synced: about 2 months ago
JSON representation
Zero-Config, Fully AI-Managed End-to-End Testing for all code gen platforms.
- Host: GitHub
- URL: https://github.com/debugg-ai/debugg-ai-mcp
- Owner: debugg-ai
- License: apache-2.0
- Created: 2025-05-28T19:10:24.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2026-04-24T20:09:39.000Z (about 2 months ago)
- Last Synced: 2026-04-24T21:31:56.092Z (about 2 months ago)
- Topics: automation, browser, end-to-end-testing, web
- Language: TypeScript
- Homepage: https://debugg.ai
- Size: 1.05 MB
- Stars: 58
- Watchers: 1
- Forks: 11
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- License: LICENSE
- Agents: AGENTS.md
Awesome Lists containing this project
- awesome-mcp - debugg-ai/debugg-ai-mcp - managed end-to-end testing ☆`79` (Developer Tools / Testing & QA)
- awesome-mcp-servers - **Debugg.AI** - Zero-Config, Fully AI-Managed End-to-End Testing for any code gen platform via Debugg.AI remote browsing test agents. `remote` `http` `ai` `git` `github` (📦 Other)
- awesome-mcp-servers - Debugg AI - Enable your code gen agents to create & run 0-config end-to-end tests against new code changes in remote browsers via the [Debugg AI](https://debugg.ai) testing platform. (Official Servers)
- toolsdk-mcp-registry - ✅ @debugg-ai/debugg-ai-mcp - configuration end-to-end testing for web applications by creating secure tunnels to local development servers and spawning testing agents that interact with web interfaces through natural language descriptions, returning detailed test results with execution recordings and screenshots. (1 tools) (node) (Browser Automation / How to Submit)
- awesome-openclaw-skills - Debugg AI - config end-to-end tests against new code changes in re... | - | (Code & Developer Tools)
README
# Debugg AI — MCP Server
AI-powered browser testing via the [Model Context Protocol](https://modelcontextprotocol.io). Point it at any URL (or localhost) and describe what to test — an AI agent browses your app and returns pass/fail with screenshots.
## Setup
Get an API key at [debugg.ai](https://debugg.ai), then add to your MCP client config:
```json
{
"mcpServers": {
"debugg-ai": {
"command": "npx",
"args": ["-y", "@debugg-ai/debugg-ai-mcp"],
"env": {
"DEBUGGAI_API_KEY": "your_api_key_here"
}
}
}
}
```
Or with Docker:
```bash
docker run -i --rm --init -e DEBUGGAI_API_KEY=your_api_key quinnosha/debugg-ai-mcp
```
## `check_app_in_browser`
Runs an AI browser agent against your app. The agent navigates, interacts, and reports back with screenshots.
| Parameter | Type | Description |
|-----------|------|-------------|
| `description` | string **required** | What to test (natural language) |
| `url` | string | Target URL — required if `localPort` not set |
| `localPort` | number | Local dev server port — tunnel created automatically |
| `environmentId` | string | UUID of a specific environment |
| `credentialId` | string | UUID of a specific credential |
| `credentialRole` | string | Pick a credential by role (e.g. `admin`, `guest`) |
| `username` | string | Username for login |
| `password` | string | Password for login |
## Configuration
```bash
DEBUGGAI_API_KEY=your_api_key
```
## Local Development
```bash
npm install && npm test && npm run build
```
## Links
[Dashboard](https://app.debugg.ai) · [Docs](https://debugg.ai/docs) · [Issues](https://github.com/debugg-ai/debugg-ai-mcp/issues) · [Discord](https://debugg.ai/discord)
---
Apache-2.0 License © 2025 DebuggAI