BarzelVault: AI Action Authorization Firewall is answering right now. Last checked moments ago.
Authorize AI agent tool calls before they run: policy-as-code, human approval, signed receipts.
Today is the operative word: we check BarzelVault: AI Action Authorization Firewall every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.
claude mcp add barzelvault-mcp --transport http https://barzelvault-mcp.mcpize.run/mcp
https://barzelvault-mcp.mcpize.run/mcp
[mcp_servers.barzelvault-mcp]
url = "https://barzelvault-mcp.mcpize.run/mcp"
{
"mcpServers": {
"barzelvault-mcp": {
"url": "https://barzelvault-mcp.mcpize.run/mcp"
}
}
}
{
"servers": {
"barzelvault-mcp": {
"type": "http",
"url": "https://barzelvault-mcp.mcpize.run/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.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://barzelvault-mcp.mcpize.run/mcp | streamable-http | sign-in | 549 ms | 0 min ago |
A local receipt and approval gate for AI agent sessions. The agent can act, but it cannot sign.
Governed access to private code for coding agents: policy, redaction, audit chain, provenance.
Commit policy as code for AI agents: check commit messages, branch names and authors before a push
Authorization answers from real policy code: evaluate Rego locally, or ask an AuthZEN 1.0 PDP.
Email inboxes for AI agents: send, reply, read verification codes, human-approved drafts.
Memory for a Claude Code agent that survives the session: five tools, a markdown vault, all local.
Receive-only inbox for AI agent sign-ups: one call returns the verification code. Never sends.
Free spend report from an agent log, no key. Hosted proxies: caps, audit export, buy calls.
Answers built from our own checks of this server.