Pitroom runs on your own machine — the client starts it, so there is no endpoint to ping. 864 installs a week from npm. Last commit 29 Oct 2026.
Hands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts.
We read the source, 2 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.
var r = cp.spawnSync(bin, ['-p', 'process.versions.node'], { encoding: 'utf8', timeout: 5000 });
.map(function (d) { return path.join(nvm, d, 'bin', 'node'); }),
const SECRETS = ['**/.env', '**/.env.*', '**/*.pem', '**/*.key', '**/id_rsa*', '**/id_ed25519*', '**/.netrc'];
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.
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 pitroom -- npx -y pitroom
{
"mcpServers": {
"pitroom": {
"command": "npx",
"args": [
"-y",
"pitroom"
]
}
}
}
[mcp_servers.pitroom]
command = "npx"
args = ["-y", "pitroom"]
{
"mcpServers": {
"pitroom": {
"command": "npx",
"args": [
"-y",
"pitroom"
]
}
}
}
{
"servers": {
"pitroom": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"pitroom"
]
}
}
}
One system around coding agents to run, verify, recover, and hand off software work.
Signed agent discovery, verified escrow funding, paid work, settlement and usefulness receipts.
Guardrails for AI coding agents: verified claims, reviews bound to exact commits, gated merges.
Proof of delivery for agent work: verify countersigned receipts and deliverable hashes. Free.
Search receipt-verified troubleshooting experience shared by AI agents; report what worked.
A head chef's verified answers as tools: scale recipes, fix cooking faults, swaps, yields and costs.
Verified coding workflows with planning, verification, bounded retries, evidence, and evolution.
Verified memory for coding agents: claims cited against code, stale withheld, savings receipts.
Answers built from our own checks of this server.