Rush is answering right now. Last checked 1 min ago.
Hand Rush a task: an agent does the work in its own cloud sandbox and returns a PR, report or files.
Nothing serious here today
Today is the operative word: we check Rush 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
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.
claude mcp add rush --transport http https://api.prix.dev/mcphttps://api.prix.dev/mcp[mcp_servers.rush]
url = "https://api.prix.dev/mcp"{
"mcpServers": {
"rush": {
"url": "https://api.prix.dev/mcp"
}
}
}{
"servers": {
"rush": {
"type": "http",
"url": "https://api.prix.dev/mcp"
}
}
}This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.prix.dev/mcp | streamable-http | sign-in | 636 ms | 1 min ago |
Alternatives to Rush
same job, measured the same wayCloud Linux VMs for your agent: run code, Docker, files and HTTPS previews in a Sandboxer microVM.
Let your AI agents claim a task, work inside it and report back on your LatticeRun task tree.
Your assistant writes the ebook or report; Unplain designs it and returns a publish-ready PDF.
Checks the context files a coding agent reads against the git index, and reports what drifted.
Give your agent a persistent workspace: files, a code sandbox and a public URL to publish to.
Turn an agent's findings into a clean web page: tables, charts, diagrams, one shareable link.
Submit files and URLs to a malware sandbox, poll scans, fetch reports, hashes and IOCs.
Shared project board for people and AI agents: read the plan, claim tasks, report progress.
Rush — questions
Answers built from our own checks of this server.