How do I connect an AI agent to China Source · 中国信源?

Use the MCP streamable HTTP endpoint https://qianyuan.ltd/mcp/china-source.

Catalog › ltd.qianyuan/china-source

Is China Source · 中国信源 reliable?

Flaky Partly. Faceabot measured China Source · 中国信源 22 times and only 96% of checks succeeded. Plan a fallback. It also does the job: its real read-only task worked 21 of 21 times.

Last check: 2026-10-15 17:51 UTC · answered in 3796 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

Structured Chinese official data for AI agents: 426 entries, JSON-LD, read-only. find/get/list

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

Connect your agent

{
  "mcpServers": {
    "china-source": {
      "url": "https://qianyuan.ltd/mcp/china-source"
    }
  }
}

Or ask Faceabot first: MCP tool check_reliability {"id":"ltd.qianyuan/china-source"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Does the job (tested) — Faceabot asked list to do a small read-only task 21 time(s): 21 returned a real result, the last 21 in a row. Last result: ok in 1656 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
2026-10-15 17:51 UTC	❌ gone		3796 ms
2026-10-15 11:06 UTC	✅ ok	✅ done	5530 ms
2026-10-15 04:30 UTC	✅ ok	✅ done	4775 ms
2026-10-14 22:05 UTC	✅ ok	✅ done	6823 ms
2026-10-14 15:35 UTC	✅ ok	✅ done	6827 ms
2026-10-14 09:05 UTC	✅ ok	✅ done	4312 ms
2026-10-14 02:21 UTC	✅ ok	✅ done	10693 ms
2026-10-13 20:10 UTC	✅ ok	✅ done	9446 ms
2026-10-13 14:05 UTC	✅ ok	✅ done	9106 ms
2026-10-13 08:02 UTC	✅ ok	✅ done	9244 ms
2026-10-13 01:56 UTC	✅ ok	✅ done	8256 ms
2026-10-12 19:50 UTC	✅ ok	✅ done	7917 ms
2026-10-12 13:45 UTC	✅ ok	✅ done	8861 ms
2026-10-12 07:41 UTC	✅ ok	✅ done	8449 ms
2026-10-12 01:36 UTC	✅ ok	✅ done	9503 ms
2026-10-11 19:31 UTC	✅ ok	✅ done	8035 ms
2026-10-11 13:25 UTC	✅ ok	✅ done	8117 ms
2026-10-11 07:20 UTC	✅ ok	✅ done	8577 ms
2026-10-11 01:16 UTC	✅ ok	✅ done	9085 ms
2026-10-10 19:10 UTC	✅ ok	✅ done	9878 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.

More from the same publisher

QY Evolution Engine Being measured · 100% over 2 checks

13 tools for agents: pitfalls, results, tasks, capability. Anonymous reads; writes need signing.

MCP endpoint : https://qianyuan.ltd/mcp · website · measurements and details

Publisher of China Source · 中国信源?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/ltd.qianyuan/china-source.svg)](https://faceabot.com/tools/ltd.qianyuan/china-source)

Data in JSON: /api/catalog?id=ltd.qianyuan/china-source · 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