Visual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.
The publisher's own command. Not a PlugMCP endpoint.
npx -y [email protected]
DUNGBEETLE_AGENT_TOKEN=<secret> DUNGBEETLE_CLIENT_ID=<value> DUNGBEETLE_CLIENT_SECRET=<secret> DUNGBEETLE_SERVER_URL=<value> claude mcp add dev.dungbeetle-mcp -- npx -y [email protected]
Run in a terminal.
{
"mcpServers": {
"dev.dungbeetle-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"DUNGBEETLE_AGENT_TOKEN": "<secret>",
"DUNGBEETLE_CLIENT_ID": "<value>",
"DUNGBEETLE_CLIENT_SECRET": "<secret>",
"DUNGBEETLE_SERVER_URL": "<value>"
}
}
}
}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchVisual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.
README is not crawled yet. Open the repository
No tool list yet. Remote servers get one after the first health check.