Wopee MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 728 installs a week from npm. Last commit 29 Oct 2026.
AI testing agents for web apps — dispatch test runs, crawls, fetch artifacts and status.
Nothing serious here today
Today is the operative word: we check Wopee MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 wopee-mcp -e 'WOPEE_API_KEY=<WOPEE_API_KEY>' -- npx -y wopee-mcp{
"mcpServers": {
"wopee-mcp": {
"command": "npx",
"args": [
"-y",
"wopee-mcp"
],
"env": {
"WOPEE_API_KEY": "<WOPEE_API_KEY>"
}
}
}
}[mcp_servers.wopee-mcp]
command = "npx"
args = ["-y", "wopee-mcp"]
env = { WOPEE_API_KEY = "<WOPEE_API_KEY>" }{
"mcpServers": {
"wopee-mcp": {
"command": "npx",
"args": [
"-y",
"wopee-mcp"
],
"env": {
"WOPEE_API_KEY": "<WOPEE_API_KEY>"
}
}
}
}{
"servers": {
"wopee-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"wopee-mcp"
],
"env": {
"WOPEE_API_KEY": "<WOPEE_API_KEY>"
}
}
}
}Put your own value in place of
<WOPEE_API_KEY> (Wopee.io API key for authentication).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
WOPEE_PROJECT_UUID (UUID of the Wopee.io project to work with), WOPEE_API_URL (Wopee.io API base URL (defaults to https://api.wopee.io)).
Alternatives to Wopee MCP
same job, measured the same wayCreate and control browser sessions for web automation, testing, and AI agent tasks
Contract testing and quality gates for spreadsheets created by AI agents.
AI split testing for any website: Luria writes page versions, runs tests and keeps winners.
Visual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.
Sendora's docs and API for coding agents: send test mail, read the log, set up webhooks.
Kineti: spend cap, undo, and test proof for AI coding agents
Run Playwright tests and surface structured results for AI agents doing test failure analysis.
MCP server for Testkube - Manage test workflows, executions, and artifacts via AI assistants
Wopee MCP — questions
Answers built from our own checks of this server.