5arz Proof Of Human is answering right now. Last checked 6 min ago. It exposes 9 tools.
Prove a real, unique human performed an action; mint a signed, verifiable Proof-of-Human credential.
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 17 August 2026. No other catalogue keeps this.
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 6 min ago.
claude mcp add 5arz-proof-of-human --transport http https://mcp.5arz.com
https://mcp.5arz.com
[mcp_servers.5arz-proof-of-human]
url = "https://mcp.5arz.com"
{
"mcpServers": {
"5arz-proof-of-human": {
"url": "https://mcp.5arz.com"
}
}
}
{
"servers": {
"5arz-proof-of-human": {
"type": "http",
"url": "https://mcp.5arz.com"
}
}
}
This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
get_attestation_receipt
get_balance
check_credential
purchase_verified_human_task
register_agent
subscribe
list_verified_human_tasks
verify_human
get_vhh_index
Tools this server used to expose. Anything built against them stopped working on the day they went.
buy_credits
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.5arz.com | streamable-http | needs auth | 40 ms | 6 min ago |
Read-only MCP server for the official ACTA verifiable credentials documentation.
Check a counterparty's verifiable Credda trust record; verify or present signed credentials.
Governed AI actions with signed, verifiable receipts: free keyless reads, human-approved writes.
Tamper-proof audit trail for AI agents. Signed receipts, offline-verifiable, zero backend.
Governance layer for agentic AI — signed, verifiable receipts for every agent action.
Append-only, signed, on-chain-verifiable agent action log — record and audit what agents did.
Hand off AI work with a signed Verification Receipt — an independent verifier proves it runs.
Sign and verify W3C Verifiable Credentials so AI agents can cryptographically authorize actions.
Answers built from our own checks of this server.