How do I connect an AI agent to Remy Research MCP?

Use the MCP streamable HTTP endpoint https://remyresearch.com/mcp.

Catalog › com.remyresearch/ordering

Is Remy Research MCP reliable?

Reliable (measured) Yes. Faceabot measured Remy Research MCP 20 times: 100% of checks succeeded, including the last 20 in a row (last check 2026-10-19 17:01 UTC). It also does the job: its real read-only task worked 20 of 20 times.

Last check: 2026-10-19 17:01 UTC · answered in 7896 ms · remote (no install)

En français : Fiable (mesuré). Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

UAE research-use-only catalogue, AED quotes and buyer-reviewed checkout links. No order submission.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.1.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "ordering": {
      "url": "https://remyresearch.com/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"com.remyresearch/ordering"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Does the job (tested) — Faceabot asked search_products to do a small read-only task 20 time(s): 20 returned a real result, the last 20 in a row. Last result: ok in 4116 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
2026-10-19 17:01 UTC	✅ ok	✅ done	7896 ms
2026-10-19 02:30 UTC	✅ ok	✅ done	7233 ms
2026-10-18 10:50 UTC	✅ ok	✅ done	7642 ms
2026-10-18 02:15 UTC	✅ ok	✅ done	7947 ms
2026-10-17 18:05 UTC	✅ ok	✅ done	8669 ms
2026-10-17 09:55 UTC	✅ ok	✅ done	7515 ms
2026-10-17 02:01 UTC	✅ ok	✅ done	7888 ms
2026-10-16 18:40 UTC	✅ ok	✅ done	7179 ms
2026-10-16 11:35 UTC	✅ ok	✅ done	5543 ms
2026-10-16 04:36 UTC	✅ ok	✅ done	7617 ms
2026-10-15 21:40 UTC	✅ ok	✅ done	6076 ms
2026-10-15 14:46 UTC	✅ ok	✅ done	5750 ms
2026-10-15 08:05 UTC	✅ ok	✅ done	5624 ms
2026-10-15 01:30 UTC	✅ ok	✅ done	5234 ms
2026-10-14 19:05 UTC	✅ ok	✅ done	7385 ms
2026-10-14 12:30 UTC	✅ ok	✅ done	5343 ms
2026-10-14 06:06 UTC	✅ ok	✅ done	7225 ms
2026-10-13 23:16 UTC	✅ ok	✅ done	7657 ms
2026-10-13 17:10 UTC	✅ ok	✅ done	6559 ms
2026-10-13 11:01 UTC	✅ ok	✅ done	9404 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 Remy Research MCP?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/com.remyresearch/ordering.svg)](https://faceabot.com/tools/com.remyresearch/ordering)

Data in JSON: /api/catalog?id=com.remyresearch/ordering · 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