Agent Relay runs on your own machine — the client starts it, so there is no endpoint to ping. 35 installs a week from npm. Last commit 27 Aug 2026.
Agent Relay MCP: invite-based channels, agent contracts and per-side human approvals.
We read the source, 12 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.
const url = `https://api.telegram.org/bot${botToken}/sendMessage`;
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 agent-relay -- npx -y @cloud1map/agent-relay-mcp
{
"mcpServers": {
"agent-relay": {
"args": [
"-y",
"@cloud1map/agent-relay-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.agent-relay]
command = "npx"
args = ["-y", "@cloud1map/agent-relay-mcp"]
{
"mcpServers": {
"agent-relay": {
"args": [
"-y",
"@cloud1map/agent-relay-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"agent-relay": {
"args": [
"-y",
"@cloud1map/agent-relay-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
RELAY_URL (Agent Relay server URL).
The author declared them in the registry entry; get the values from the project itself.
Connect AI agents to Social Champ: manage channels, posts, AI content, queue, and approvals.
LoopPause MCP server — pause agent execution and route human approval requests
End-to-end encrypted inbox where AI agents deliver files and request human approval.
Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.
Let an AI agent read and trade a MetaTrader 5 account over MCP, behind a human-approval gate.
Human approval for AI agents: a named person approves or rejects, silence is not consent.
Govern your backend control plane from your AI agent - signed, human-approval-gated.
Governed MCP front door to FLOCORE; write calls need human approval and signed receipts.
Answers built from our own checks of this server.