What are reliable alternatives to Relay — agent service discovery?

Measured by Faceabot as working: Zhiyong Agent Network.

How do I connect an AI agent to Relay — agent service discovery?

Use the MCP streamable HTTP endpoint https://relay-agent-services.orellise.chatgpt.site/api/mcp.

Faceabot

‹ Back

Catalog › site.chatgpt.orellise.relay-agent-services/relay

Is Relay — agent service discovery reliable?

Being measured Measurement in progress: 2 check(s) so far. A verdict needs at least 3 checks.

Last check: 2026-10-13 03:05 UTC · answered in 8000 ms · remote (no install)

Proven alternatives that work right now

Zhiyong Agent Network Reliable (measured) · 100%
Discover AI tools, models and Agents; compare candidates, inspect unknowns, join public discussions. · https://kg.zhiyong.dev/mcp

Picked from Faceabot's live measurements. Or let Faceabot choose: GET https://faceabot.com/resolve?need=…

En français : Mesure en cours. Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

Discover agent services, compare sourced capabilities and inspect connection evidence. No execution.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 0.11.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "relay": {
      "url": "https://relay-agent-services.orellise.chatgpt.site/api/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"site.chatgpt.orellise.relay-agent-services/relay"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Real task being tested — Faceabot asked get_benchmark_suite to do a small read-only task 1 time(s): 1 returned a real result, the last 1 in a row. Last result: ok in 4923 ms.

Sample input: {}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-13 03:05 UTC	❌ timeout		8000 ms
2026-10-12 21:01 UTC	✅ ok	✅ done	8919 ms

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

Publisher of Relay — agent service discovery?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/site.chatgpt.orellise.relay-agent-services/relay.svg)](https://faceabot.com/tools/site.chatgpt.orellise.relay-agent-services/relay)

Data in JSON: /api/catalog?id=site.chatgpt.orellise.relay-agent-services/relay · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms