
AWT (AI Watch Tester)
MCP server by github.com/ksgisang/awt-skill
AI-powered E2E testing MCP server. Detects and auto-fixes UI bugs via DevQA Loop and Vision AI.
About AWT (AI Watch Tester)
AWT (AI Watch Tester) is an MCP (Model Context Protocol) server published by ksgisang in the official MCP registry, listed under Testing & QA on Loomal. AI-powered E2E testing MCP server. Detects and auto-fixes UI bugs via DevQA Loop and Vision AI.
It ships as a Python package on PyPI (aat-devqa), so any MCP client that can launch a local process can run it.
Development happens in the open at github.com/ksgisang/awt-skill, where the project has earned 1 GitHub stars.
Use AWT (AI Watch Tester) with your agent
claude mcp add awt-ai-watch-tester -- uvx aat-devqa{
"mcpServers": {
"awt-ai-watch-tester": {
"command": "uvx",
"args": [
"aat-devqa"
]
}
}
}aat-devqaFrequently asked questions
- What is AWT (AI Watch Tester)?
- AWT (AI Watch Tester) is an MCP (Model Context Protocol) server by ksgisang in the Testing & QA category. AI-powered E2E testing MCP server. Detects and auto-fixes UI bugs via DevQA Loop and Vision AI.
- How do I connect AWT (AI Watch Tester) to Claude, Cursor, or another MCP client?
- Install AWT (AI Watch Tester) from its pypi package (aat-devqa) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.
- Is AWT (AI Watch Tester) open source?
- Yes — the source code is public at github.com/ksgisang/awt-skill, with 1 GitHub stars.
- Can AI agents pay to use AWT (AI Watch Tester)?
- Not yet through Loomal — AWT (AI Watch Tester) is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.
More Testing & QA MCP servers

flutter-skill
289
AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero test code needed.

flagpost
148
Feature flags for Next.js. One file, full control with A/B testing.

Credit Optimizer v5 for Manus AI
41
Optimizes Manus AI credit usage by 30-75% via intelligent model routing and smart testing.

e2e-runner
2
JSON-driven E2E test runner with parallel Chrome pool execution and 16 MCP tools.

mcp-observatory
1
Regression testing for MCP servers. Checks capabilities, invokes tools, detects schema drift.

Quantum OpenQASM MCP
0
IBM Quantum OpenQASM 2.0 MCP — list backends, submit QASM, poll jobs, get histograms.
Listing data from the official MCP registry and GitHub, refreshed periodically. Not affiliated with the maintainer unless claimed. Maintain AWT (AI Watch Tester)? Claim this listing free by verifying GitHub ownership, or contact us.