AI 客服国标合规知识库 (GB/T 47746—2026) MCP server
online · 96% uptime中国 AI 客服国标 GB/T 47746—2026 合规知识库:条款级问答 + 全部 61 项达标自查清单(48 应 + 4 宜 + 9 可,含 5 项一票否决),答案标注条款依据。
1 stars
Reviews
Write oneNobody has reviewed AI 客服国标合规知识库 (GB/T 47746—2026) yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
AI 客服国标合规知识库 (GB/T 47746—2026) tools (5)
write = sends, deletes, buys or postsget_answerFree按 slug 取一条问答的完整内容(正文 + 要点 + 标准条款依据 + 常见追问)。 Args: slug: 问答标识,先用 list_questions 或 search_answers 取得
list_questionsFree列出全部合规问答的标题清单。 Args: cluster: 可选,按集群过滤。可选值 ai-service-standard(AI客服国标) / enterprise-knowledge-base(企业知识库)
search_answersFree按关键词检索合规问答,返回最相关的若干条(含简要答案)。 Args: query: 检索词,如「转人工」「备案 登记」「知识库 切分」 top_k: 返回条数,默认 5
self_check_listFree取 GB/T 47746-2026 的自查清单:企业对照检查自家 AI 客服是否达标。 返回**清单本体**(61 项:id / 条款 / 等级 / 是否一票项 / 要求 / 怎么补), 外加一票项速查与用途说明;解释「61 项怎么来的」那篇原子随附在 explainer 字段。
standard_infoFree获取 GB/T 47746-2026 标准的元信息(发布/实施日期、归口、篇幅、核心要求)。
Public scan report
scanner v0.1.10 · 2026-10-14 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 4270ms17/20
- Tool poisoning5 tool descriptions checked15/15
- Auth qualityopen endpoint, read-only tools10/15
- Maintenancelast push 9 days ago15/15
- Maintainer identityregistry namespace matches repository owner; website matches verified namespace8/10
How AI 客服国标合规知识库 (GB/T 47746—2026) compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 87/100
- higher than 73% of 48,255 servers
- Tools
- 5
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 96%
- of our recent checks; the typical remote server answers 100%
- Response time
- 1,637 ms
- faster than 5% of 30,031 servers
- GitHub stars
- 1
- more than 65% of 28,688 servers
What its tools let an agent do: 5 read
Release history: 2 versions in the registry since 2026-09-11, latest 2026-10-03, typically one every 22 days.
Install AI 客服国标合规知识库 (GB/T 47746—2026) in Claude Code, Cursor or VS Code
claude mcp add --transport http answers https://savantcat.cn/mcp
What the publisher says
From the AI 客服国标合规知识库 (GB/T 47746—2026) repository's README, as published. We do not edit it. Read it on GitHub
savantcat-answers-mcp
把中国 AI 客服国标 GB/T 47746—2026 变成 Agent 能直接调用的工具。
An MCP server for China's GB/T 47746—2026 AI customer-service compliance standard.
为什么值得接
2026-09-01 已经实施了。 只要你在用 AI 客服,这份标准的合规问题就绕不过去 —— 而标准原文 40 多页、条款密度极高,「AI 客服怎么算达标」散落在 4~9 章里,人工翻效率极低。
这个 MCP 把条款级问答做成工具:答案全部标注条款出处,Agent 一问即得,不用装、不用 Key、公开只读。
这是什么
GB/T 47746—2026《顾客联络服务 人工与智能客户服务协同要求》是中国第一个聚焦「人工客服与智能客服协同机制」的国家标准,2026-05-25 发布、2026-09-01 实施。
这个 MCP Server 把该标准的合规问答做成了 Agent 可以直接调用的工具。任何支持 MCP 的客户端(Claude Desktop、Cursor、Cline、自研 Agent)连上就能问:
- 「AI 客服怎么过国标?」
- 「哪 5 类场景必须自动转人工?」
- 「AI 客服的自查项到底有多少条?」
- 「上线要走备案还是登记?」
所有答案都标注标准条款依据。
直接用(无需安装)
已部署在公网,公开只读、不需要 API Key:
https://savantcat.cn/mcp传输方式 streamable-http,无状态。接入文档:https://savantcat.cn/mcp/
可用工具
接入
Claude Desktop
编辑 claudedesktopconfig.json:
{
"mcpServers": {
"savantcat-answers": {
"url": "https://savantcat.cn/mcp"
}
}
}Cursor
编辑 .cursor/mcp.json:
{
"mcpServers": {
"savantcat-answers": {
"url": "https://savantcat.cn/mcp"
}
}
}腾讯 WorkBuddy / CodeBuddy
WorkBuddy 与 CodeBuddy 原生支持远程 HTTP MCP。打开侧边栏 插件 → MCP 服务器 → 配置 MCP,把下面这段粘进 mcp.json 即可(用户级 ~/.workbuddy/mcp.json,项目级 <项目目录>/.workbuddy/mcp.json):
{
"mcpServers": {
"savantcat-answers": {
"type": "http",
"url": "https://savantcat.cn/mcp"
}
}
}保存后新建一次会话(或在 MCP 列表点「信任」)即生效。公网只读、不需要 Key,也不用装 Node.js 或任何本地进程。
Hermes Agent
mcp_servers:
savantcat-answers:
connect_timeout: 20
enabled: true
url: https://savantcat.cn/mcp任意 MCP 客户端 / 自研 Agent
标准 MCP streamable-http 握手即可:
curl -X POST https://savantcat.cn/mcp \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize",
"params":{"protocolVersion":"2025-06-18","capabilities":{},
"clientInfo":{"name":"my-agent","version":"1.0"}}}'自托管
想换成你自己的内容?把 data/ 里的 JSON 替换掉即可。
pip install -r requirements.txt
# 本地 stdio 通道(给桌面客户端用)
python server.py
# 远程 HTTP 通道
python server.py --transport http --host 0.0.0.0 --port 8765 --stateless
# 自检:不走协议,直接打全部工具
python server.py --selftestDocker
docker build -t savantcat-answers-mcp .
docker run -p 8765:8765 savantcat-answers-mcp --transport http --host 0.0.0.0 --port 8765 --stateless公网部署提示:MCP SDK 默认开启 DNS-rebinding 防护,只放行 localhost,用真实域名访问会得到 421 Invalid Host header。本项目通过 TransportSecuritySettings 把你的域名加入白名单(保留防护,而不是关掉),见 server.py 的 DEFAULTALLOWEDHOSTS——部署前记得改成你自己的域名。
数据
data/ 下三个文件:
data/answers.json 12 条原子问答全文(含 facts / sources / faqs / body_md)
data/index.json 轻量索引(列表与检索用)
data/meta.json 集群元信息每个原子问答都带 sources 字段,标注条款出处。
项目结构
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-10-14restoreD → Ascore 87
- 2026-09-19downgradeA → Dscore 47: Remote endpoint did not respond
AI 客服国标合规知识库 (GB/T 47746—2026): common questions
- Is AI 客服国标合规知识库 (GB/T 47746—2026) MCP server safe?
- Yes, by our scan: it is graded A (87/100). Read the AI 客服国标合规知识库 (GB/T 47746—2026) safety report
- How do I install AI 客服国标合规知识库 (GB/T 47746—2026)?
- It runs remotely at savantcat.cn. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does AI 客服国标合规知识库 (GB/T 47746—2026) need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is AI 客服国标合规知识库 (GB/T 47746—2026) maintained?
- The last commit was 30 days ago (2026-10-05). The latest release is v1.1.0.
- Is AI 客服国标合规知识库 (GB/T 47746—2026) up?
- 96% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does AI 客服国标合规知识库 (GB/T 47746—2026) compare with other MCP servers?
- safety score 87/100 (higher than 73% of 48,255 servers); tools 5 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.