Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

AI 客服国标合规知识库 (GB/T 47746—2026)

REMOTE · SAVANTCAT.CN · SCANNED SEP 24

中国 AI 客服国标 GB/T 47746—2026 合规问答库:必须自动转人工的场景、强制自查项、上线备案要求,答案标注条款依据。

Available components

+11 this week 78 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security80
Transport & Reachability100
Schema Quality & AI Usability77
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 397 tokens (~79/item across 5 items; 5 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management43
  • Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
Install

How do I install the AI 客服国标合规知识库 (GB/T 47746—2026) MCP server?

AI 客服国标合规知识库 (GB/T 47746—2026) is a hosted endpoint at https://savantcat.cn/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · savantcat.cn

# add to Claude Code
claude mcp add --transport http cn-savantcat-answers 'https://savantcat.cn/mcp'
// .cursor/mcp.json
{
  "mcpServers": {
    "cn-savantcat-answers": {
      "url": "https://savantcat.cn/mcp"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "cn-savantcat-answers": {
      "type": "http",
      "url": "https://savantcat.cn/mcp"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.cn-savantcat-answers]
url = "https://savantcat.cn/mcp"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cn-savantcat-answers": {
      "type": "remote",
      "url": "https://savantcat.cn/mcp",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add cn-savantcat-answers --url 'https://savantcat.cn/mcp' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  cn-savantcat-answers:
    url: "https://savantcat.cn/mcp"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "cn-savantcat-answers": {
      "Transport": "http",
      "Url": "https://savantcat.cn/mcp"
    }
  }
}
# add to Vellum
assistant mcp add cn-savantcat-answers -t streamable-http -u 'https://savantcat.cn/mcp'
// mcp.json
{
  "mcpServers": {
    "cn-savantcat-answers": {
      "type": "http",
      "url": "https://savantcat.cn/mcp"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 24 Sept 26 +1
    • Authorization: unverified → partial security
    • Injection markers: unverified → pass security
    • TLS certificate: unverified → pass security
    • HSTS header: unverified → pass security
    • Transport: fail → pass security
    • Endpoint reachability: unreachable → reachable functional
    • Tool coverage: unverified → 100 functional
    • Stability: unverified → 0.43 functional
    • MCP protocol: unverified → pass functional
  • 23 Sept 26 0
    • Endpoint reachability: reachable → unreachable security
    • Stability: 0.37 → unverified security
    • Authorization: partial → unverified security
    • Tool safety: pass → unverified security
    • TLS certificate: pass → unverified security
    • HSTS header: pass → unverified security
    • Transport: pass → fail security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
  • 22 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +8
    • Authorization: unverified → partial security
    • Injection markers: unverified → pass security
    • TLS certificate: unverified → pass security
    • HSTS header: unverified → pass security
    • Transport: fail → pass security
    • Endpoint reachability: unreachable → reachable functional
    • Tool coverage: unverified → 100 functional
    • Stability: unverified → 0.23 functional
    • MCP protocol: unverified → pass functional
  • 17 Sept 26 0
    • Endpoint reachability: reachable → unreachable security
    • Tool safety: pass → unverified security
    • TLS certificate: pass → unverified security
    • Stability: 0.17 → unverified security
    • HSTS header: pass → unverified security
    • Transport: pass → fail security
    • Authorization: Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
    • First check of Schema quality: unverified functional
  • 15 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Sept 2026 · Probed https://savantcat.cn/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=savantcat.cn CN=Encryption Everywhere DV TLS CA - G2,OU=www.digicert.com,O=DigiCert Inc,C=US 11 Aug 2026 8 Nov 2026 RSA 2048 SHA256-RSA ce7be013207e24787f0c9c22bc11201
SANs: savantcat.cn, www.savantcat.cn
CN=Encryption Everywhere DV TLS CA - G2,OU=www.digicert.com,O=DigiCert Inc,C=US (CA) CN=DigiCert Global Root G2,OU=www.digicert.com,O=DigiCert Inc,C=US 27 Nov 2017 27 Nov 2027 RSA 2048 SHA256-RSA de0ffb5ee62cb61109f608c9ced5ed3

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of savantcat.cn. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
cn. present 33094 8 Verified
savantcat.cn. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=31536000; includeSubDomains
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin
permissions-policy geolocation=(), microphone=(), camera=(), payment=(), usb=(), magnetometer=(), gyroscope=()

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://savantcat.cn/mcp Verified 200
http (plaintext) http://savantcat.cn/mcp HTTPS enforced 301 https://savantcat.cn/mcp
MCP tools · 5 exposed · ~291 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
get_answer ~67

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

NameTypeReqDescription
slugstringyes
NameTypeReqDescription
resultstringyes

No examples provided.

list_questions ~65

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)

NameTypeReqDescription
clusterstring
NameTypeReqDescription
resultstringyes

No examples provided.

search_answers ~84

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

NameTypeReqDescription
querystringyes
top_kinteger
NameTypeReqDescription
resultstringyes

No examples provided.

self_check_list ~38

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。

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

standard_info ~37

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)。

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

Common questions

What is the AI 客服国标合规知识库 (GB/T 47746—2026) MCP server?

AI 客服国标合规知识库 (GB/T 47746—2026) is an MCP server listed in the public MCP registry as cn.savantcat/answers. 中国 AI 客服国标 GB/T 47746, 2026 合规问答库:必须自动转人工的场景、强制自查项、上线备案要求,答案标注条款依据。 This page covers its hosted endpoint (https://savantcat.cn/mcp).

Is the AI 客服国标合规知识库 (GB/T 47746—2026) MCP server safe to use?

AI 客服国标合规知识库 (GB/T 47746—2026) scores 78 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the AI 客服国标合规知识库 (GB/T 47746—2026) MCP server expose?

AI 客服国标合规知识库 (GB/T 47746—2026) exposes 5 tools: list_questions, search_answers, get_answer, self_check_list, standard_info. Their descriptions and schemas cost roughly 291 tokens of context every time the server is loaded.

Does the AI 客服国标合规知识库 (GB/T 47746—2026) MCP server require authentication?

No. We connected to AI 客服国标合规知识库 (GB/T 47746—2026) without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the AI 客服国标合规知识库 (GB/T 47746—2026) MCP server still maintained?

AI 客服国标合规知识库 (GB/T 47746—2026) is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.