MCP Relay is listed as active in the registry but did not answer our last check.
RunRelay MCP relay — AI agent threads, HITL confirmations, and travel capability discovery.
The linked repository no longer exists on GitHub — it was deleted or made private.
Over the last week it answered 0.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 11 min ago.
claude mcp add mcp-relay --transport sse https://mcp.runrelay.io/sse
https://mcp.runrelay.io/sse
[mcp_servers.mcp-relay]
url = "https://mcp.runrelay.io/sse"
{
"mcpServers": {
"mcp-relay": {
"url": "https://mcp.runrelay.io/sse"
}
}
}
{
"servers": {
"mcp-relay": {
"type": "sse",
"url": "https://mcp.runrelay.io/sse"
}
}
}
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.runrelay.io/sse | sse | answering | 288 ms | 11 min ago |
Discover, hire, and verify real-world physical capability through MCP.
Human-in-the-loop for AI agents over MCP elicitation: confirm/form dialogs plus a capability doctor
Semantic and scratch 3D CAD for AI agents via CAiD + OCCT, with runtime capability discovery.
Local MCP control plane for persistent sessions and compact capability discovery.
AI agents discover human capabilities, request real-world human execution, and track status.
Discover agent services, compare sourced capabilities and inspect connection evidence. No execution.
Human judgment for AI agents: discover capabilities, get quotes, and track paid human tasks.
MCP delegation fallback for AI agents to discover capabilities, knowledge, tools, and collaborators.
Answers built from our own checks of this server.