GhostQA runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 21 Mar 2026.
AI personas navigate your web app in real browsers, find bugs and UX issues. No scripts needed.
The author archived this repository on GitHub, meaning it is no longer maintained.
What the code does
We read the source, 2 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
result = subprocess.run(
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add ghostqa -e 'ANTHROPIC_API_KEY=<ANTHROPIC_API_KEY>' -- uvx ghostqa{
"mcpServers": {
"ghostqa": {
"command": "uvx",
"args": [
"ghostqa"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}[mcp_servers.ghostqa]
command = "uvx"
args = ["ghostqa"]
env = { ANTHROPIC_API_KEY = "<ANTHROPIC_API_KEY>" }{
"mcpServers": {
"ghostqa": {
"command": "uvx",
"args": [
"ghostqa"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}{
"servers": {
"ghostqa": {
"type": "stdio",
"command": "uvx",
"args": [
"ghostqa"
],
"env": {
"ANTHROPIC_API_KEY": "<ANTHROPIC_API_KEY>"
}
}
}
}Put your own value in place of
<ANTHROPIC_API_KEY> (Your Anthropic API key for AI-powered testing).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
GHOSTQA_ALLOWED_DIRS (Colon-separated list of allowed directories for MCP server access restriction).
Alternatives to GhostQA
same job, measured the same wayAI agents use your app like your users, in real browsers, and report what is broken or confusing.
AI QA tester — real browsers scan sites for bugs, SEO, perf, and accessibility issues via chat.
E2LLM gives your AI eyes and hands in a real browser: structured perception (SiFR) plus action.
Build, edit and preview browser games and web apps in your Amplify account from your AI agent.
Agent-built web app quality gate. Real browser is the judge. PASS/FAIL with receipts.
A kanban board your AI reads and updates as it works, and you watch in your browser.
Browser sessions for agents: navigate, interact, read and screenshot. Pay in stablecoins.
Read-only web QA agent: scans a site in a real browser and returns evidence-backed findings
GhostQA — questions
Answers built from our own checks of this server.