Purgatory (p7y) is listed as active in the registry but did not answer our last check. Last commit 6 Nov 2026.
Self-hosted Docker sandboxes for agents: create one, deploy a compose stack, read its files and URLs
We read the source, 1 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.
.map(f => { try { return fs.statSync(path.join(dir, f)).mtimeMs } catch { return 0 } })
function spawn(anywhere) {
const result = await vm.runInNewContext(`(async () => { ${script} })()`, context) as unknown
- /var/run/docker.sock:/var/run/docker.sock
if (el) el.innerHTML = `<span class="dot starting"></span>starting ${String(r.service || 'the app').replace(/[&<>"']/g, '')}…`
return true
<h3>SSH (~/.ssh/config)</h3><pre class="code" data-connect-ssh></pre>
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.
claude mcp add p7y --transport http 'https://{purgatory_host}/mcp'
https://{purgatory_host}/mcp
[mcp_servers.p7y]
url = "https://{purgatory_host}/mcp"
{
"mcpServers": {
"p7y": {
"url": "https://{purgatory_host}/mcp"
}
}
}
{
"servers": {
"p7y": {
"type": "http",
"url": "https://{purgatory_host}/mcp"
}
}
}
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://{purgatory_host}/mcp | streamable-http | answering | 0 ms | 3 min ago |
Deploy files, sites, and Dockerfile apps to live URLs + private drives for agent memory.
Hosted MCP for creating, checking, deploying, and hosting static sites for AI agents.
Hosted MCP for creating, checking, deploying, and hosting static sites for AI agents.
Deploy and manage web apps on InstaPods: create pods, push files, run commands, read logs.
Deploy static sites from AI agents: deploy_site publishes files and returns a live URL in seconds.
Secure Umami Analytics MCP server for Cloud and self-hosted deployments
Agent-first hosting: create apps, push code, and deploy to HTTPS URLs from your coding agent.
Docker for AI agents — containers, compose stacks, logs and databases, locally or over SSH.
Answers built from our own checks of this server.