Vibe Test — Browser Testing Agent runs on your own machine — the client starts it, so there is no endpoint to ping. 207 installs a week from npm. Last commit 15 Oct 2026.
Code-aware browser testing agent — 14 Playwright tools for AI code editors via MCP
We read the source, 3 d ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
await fs.writeFile(reportPath, `${JSON.stringify(diagnostic, null, 2)}\n`, 'utf8')
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.
const content = await readFile(path.join(codebasePath, filePath))
const child = spawn(process.execPath, [cliPath, ...args], {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
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 vibe-testing -- npx -y vibe-testing
{
"mcpServers": {
"vibe-testing": {
"command": "npx",
"args": [
"-y",
"vibe-testing"
]
}
}
}
[mcp_servers.vibe-testing]
command = "npx"
args = ["-y", "vibe-testing"]
{
"mcpServers": {
"vibe-testing": {
"command": "npx",
"args": [
"-y",
"vibe-testing"
]
}
}
}
{
"servers": {
"vibe-testing": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"vibe-testing"
]
}
}
}
Playwright Tools for MCP
Playwright Tools for MCP
Ultra-lightweight browser engine for AI agents. 33 MCP tools, 4 SDKs, cross-platform.
KATATAN E2E testing agent set — Playwright + KATATAN MCP integration
MCP server for Safari DevTools — browser debugging and automation for AI coding agents
262 MCP tools for agent-native control of openDAW, a browser-based DAW
MCP server for browser automation via Vercel's agent-browser CLI
Human-to-AI code review bridge. Review UI in the browser, AI agents fix code via MCP.
Answers built from our own checks of this server.