How do I connect an AI agent to prime-refund-tools?

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

Catalog › com.primesettlementrefund/prime-refund-tools

Is prime-refund-tools reliable?

Reliable (measured) Yes. Faceabot measured prime-refund-tools 18 times: 100% of checks succeeded, including the last 18 in a row (last check 2026-10-19 20:45 UTC).

Last check: 2026-10-19 20:45 UTC · answered in 7841 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

Amazon Prime refund tools: eligibility check, payment amount estimator, and claim deadline guide.

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.0 · publisher website

Connect your agent

{
  "mcpServers": {
    "prime-refund-tools": {
      "url": "https://mcp.primesettlementrefund.com/mcp"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"com.primesettlementrefund/prime-refund-tools"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Not tested with a real task yet. Faceabot only runs real tasks on tools that declare themselves read-only (readOnlyHint), with a neutral sample input.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-19 20:45 UTC	✅ ok	—	7841 ms
2026-10-19 07:55 UTC	✅ ok	—	5804 ms
2026-10-18 15:20 UTC	✅ ok	—	4376 ms
2026-10-18 04:40 UTC	✅ ok	—	4991 ms
2026-10-17 20:45 UTC	✅ ok	—	4098 ms
2026-10-17 12:20 UTC	✅ ok	—	4114 ms
2026-10-17 04:40 UTC	✅ ok	—	5383 ms
2026-10-16 21:00 UTC	✅ ok	—	5723 ms
2026-10-16 13:55 UTC	✅ ok	—	6646 ms
2026-10-16 07:01 UTC	✅ ok	—	8587 ms
2026-10-16 00:10 UTC	✅ ok	—	6484 ms
2026-10-15 17:16 UTC	✅ ok	—	9485 ms
2026-10-15 10:36 UTC	✅ ok	—	5172 ms
2026-10-15 04:05 UTC	✅ ok	—	2596 ms
2026-10-14 21:40 UTC	✅ ok	—	4898 ms
2026-10-14 15:10 UTC	✅ ok	—	5378 ms
2026-10-14 08:45 UTC	✅ ok	—	3198 ms
2026-10-14 02:01 UTC	✅ ok	—	8891 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 prime-refund-tools?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/com.primesettlementrefund/prime-refund-tools.svg)](https://faceabot.com/tools/com.primesettlementrefund/prime-refund-tools)

Data in JSON: /api/catalog?id=com.primesettlementrefund/prime-refund-tools · 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