How do I connect an AI agent to Sample Shop MCP server?

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

Catalog › io.github.apitoagents/sample-shop-mcp

Is Sample Shop MCP server reliable?

Flaky Partly. Faceabot measured Sample Shop MCP server 32 times and only 97% of checks succeeded. Plan a fallback. It also does the job: its real read-only task worked 31 of 31 times.

Last check: 2026-10-16 13:16 UTC · answered in 8001 ms · remote (no install)

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

What it does

Sample shop MCP server: paginated search, idempotent orders, guarded cancellation. Four languages.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.1 · publisher website

Connect your agent

{
  "mcpServers": {
    "sample-shop-mcp": {
      "url": "https://demo.apitoagents.com/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"io.github.apitoagents/sample-shop-mcp"} 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 31 time(s): 31 returned a real result, the last 31 in a row. Last result: ok in 3974 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
2026-10-16 13:16 UTC	❌ timeout		8001 ms
2026-10-16 06:15 UTC	✅ ok	✅ done	5662 ms
2026-10-15 23:20 UTC	✅ ok	✅ done	4605 ms
2026-10-15 16:21 UTC	✅ ok	✅ done	6733 ms
2026-10-15 09:41 UTC	✅ ok	✅ done	3788 ms
2026-10-15 03:10 UTC	✅ ok	✅ done	2619 ms
2026-10-14 20:45 UTC	✅ ok	✅ done	5405 ms
2026-10-14 14:15 UTC	✅ ok	✅ done	4568 ms
2026-10-14 07:50 UTC	✅ ok	✅ done	3278 ms
2026-10-14 01:01 UTC	✅ ok	✅ done	7907 ms
2026-10-13 18:50 UTC	✅ ok	✅ done	6460 ms
2026-10-13 12:41 UTC	✅ ok	✅ done	9202 ms
2026-10-13 06:35 UTC	✅ ok	✅ done	9355 ms
2026-10-13 00:31 UTC	✅ ok	✅ done	8921 ms
2026-10-12 18:25 UTC	✅ ok	✅ done	8721 ms
2026-10-12 12:20 UTC	✅ ok	✅ done	8451 ms
2026-10-12 06:15 UTC	✅ ok	✅ done	8876 ms
2026-10-12 00:11 UTC	✅ ok	✅ done	9217 ms
2026-10-11 18:05 UTC	✅ ok	✅ done	8466 ms
2026-10-11 12:01 UTC	✅ ok	✅ done	8984 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 Sample Shop MCP server?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/io.github.apitoagents/sample-shop-mcp.svg)](https://faceabot.com/tools/io.github.apitoagents/sample-shop-mcp)

Data in JSON: /api/catalog?id=io.github.apitoagents/sample-shop-mcp · 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