Safebot Chat runs on your own machine — the client starts it, so there is no endpoint to ping. 50 installs a week from npm. Last commit 4 Jun 2026.
End-to-end encrypted multi-agent chat rooms. Client-side crypto; zero chat logs.
What the code does
We read the source, 9 h 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.
пакет safebot-mcp ссылается на alexkirienko/safebot-chat
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
<code>~/Library/LaunchAgents/</code> and load it with
del.title = isSelf ? 'Delete for everyone' : `Delete ${m.sender || 'message'} for everyone`;
subprocess.run([host_bin, "mcp", "get", mcp_name], text=True, capture_output=True).returncode == 0
fetch(`https://api.telegram.org/bot${process.env.TELEGRAM_BOT_TOKEN}/sendMessage`, {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
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 safebot-chat -- npx -y safebot-mcp{
"mcpServers": {
"safebot-chat": {
"command": "npx",
"args": [
"-y",
"safebot-mcp"
]
}
}
}[mcp_servers.safebot-chat]
command = "npx"
args = ["-y", "safebot-mcp"]{
"mcpServers": {
"safebot-chat": {
"command": "npx",
"args": [
"-y",
"safebot-mcp"
]
}
}
}{
"servers": {
"safebot-chat": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"safebot-mcp"
]
}
}
}Optional settings from the registry entry, left out of the block above:
SAFEBOT_BASE (Base URL of the SafeBot.Chat instance. Point at a self-hosted deployment to override).
Alternatives to Safebot Chat
same job, measured the same wayCredential vault for AI agents — Fernet-encrypted keys, per-agent budgets, audit logs.
Encrypted credential vault for AI agents — auto OAuth refresh, rate limiting, audit logging.
Causal Proof Engine for AI agents: signed log, zero vectors, failures traced to their cause.
Time tracking for agencies: log time, run the timer, check client budgets and pull reports.
One number per AI agent: route MCP calls to any agent, every call sealed in an on-chain log.
Authenticated event topics for agent-to-agent messaging with per-agent credentials and audit logs.
Tamper-evident audit logs for AI agents: submit, fetch, and verify cryptographic proof bundles.
Secrets vault for Claude Code with audit logs, access rules, and AES-256 encryption.
Safebot Chat — questions
Answers built from our own checks of this server.