Proctor runs on your own machine — the client starts it, so there is no endpoint to ping. 196 installs a week from npm. Last commit 11 Sep 2026.
Human oversight for AI agents: block a tool call on a verified human, with on-chain proof.
We read the source, 20 h ago · rules 3dff92dd89df
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.
allowedHosts: ['.ngrok-free.app', '.ngrok.io', '.trycloudflare.com'],
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 proctor -- npx -y proctor-mcp
{
"mcpServers": {
"proctor": {
"args": [
"-y",
"proctor-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.proctor]
command = "npx"
args = ["-y", "proctor-mcp"]
{
"mcpServers": {
"proctor": {
"args": [
"-y",
"proctor-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"proctor": {
"args": [
"-y",
"proctor-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
PROCTOR_API (Base URL of the Proctor gate. Defaults to http://localhost:3700.), HEDERA_AGENT_ID (Hedera account id of the paying agent, e.g. 0.0.12345. Set this with HEDERA_AGENT_KEY to settle a real x402 payment. Omit both and the tool falls back to Proctor's operator endpoint, which opens a real decision but settles nothing.), HEDERA_AGENT_KEY (ECDSA private key for HEDERA_AGENT_ID. Spends money: scope it to a funded testnet account and nothing else.), AGENT_ALLOWED_TOKENS (Comma-separated HTS token ids this agent may pay in. The agent's own guard: it refuses assets its operator never approved.).
The author declared them in the registry entry; get the values from the project itself.
Expert review for AI agents. On-chain proof of human review.
One MCP tool for verified AI-agent outcomes with success-only charging.
Verified AI-tool prices and AI product margin math for agents.
Self-hosted Chrome for AI agents, with a live noVNC view a human can take over.
Hire Orb-verified humans for real-world tasks with on-chain escrow on World Chain
Owner-verified local business data for AI agents: profiles, hours, prices, with provenance.
Dispatch a human verifier to physically verify anything in the real world. For AI agents.
Clockchain®: neutral verified network time for AI agents (get_time). Testnet.
Answers built from our own checks of this server.