Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "answers": {
      "type": "http",
      "url": "https://savantcat.cn/mcp"
    }
  }
}

claude mcp add --transport http answers https://savantcat.cn/mcp

[mcp_servers.answers]
url = "https://savantcat.cn/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "answers": {
      "type": "remote",
      "url": "https://savantcat.cn/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "answers": {
      "type": "http",
      "url": "https://savantcat.cn/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=answers&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vc2F2YW50Y2F0LmNuL21jcCJ9"
}

{
  "servers": {
    "answers": {
      "type": "http",
      "url": "https://savantcat.cn/mcp"
    }
  }
}

{
  "mcpServers": {
    "answers": {
      "httpUrl": "https://savantcat.cn/mcp"
    }
  }
}

extensions:
  "answers":
    enabled: true
    name: "answers"
    type: streamable_http
    uri: "https://savantcat.cn/mcp"
    timeout: 300

Quality 78 / 100good

protocol88 · weight 25

pass
protocol.modernsupports 2026-07-28 (server/discover)
pass
protocol.statelessanswers without a session
pass
protocol.transportstreamable HTTP
warn
protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene71 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
fail
tools.annotationsno tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: list_questions (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); self_check_list (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); standard_info (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
pass
tools.token_costabout 300 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability75 · weight 15

warn
stability.changes6 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

5 tools, about 300 tokens to load them all · tool set 14e93929514e · tools last changed 2026-10-06 · checked 2026-10-20 20:46 UTC

Tool changes

2026-10-06standard_infochangedannotations
2026-10-06self_check_listchangeddescription, annotations
before
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法；「61 项怎么来的」那篇解释文随附在 explainer 字段。
after · 100% of words in common
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。
2026-10-06get_answerchangedannotations
2026-10-06search_answerschangedannotations
2026-10-06list_questionschangedannotations
2026-10-04self_check_listchangeddescription
before
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。
after · 63% of words in common
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法；「61 项怎么来的」那篇解释文随附在 explainer 字段。

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 98 / 100

provenance100

liveness94

freshness100

hygiene100

+repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-84% +updated-17d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://savantcat.cn/mcp` streamable-http	none	yes	84%	2639 ms	2026-07-28	2026-10-20

Tools (5)

`get_answer`	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_questions`	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_answers`	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_list`	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_info`	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）。

Schemas: list_tools.

Similar MCP servers

More from cn.savantcat

Official server.json

{
  "name": "cn.savantcat/answers",
  "title": "AI 客服国标合规知识库 (GB/T 47746—2026)",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://savantcat.cn/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.1.0",
  "repository": {
    "url": "https://github.com/savantcat/savantcat-answers-mcp",
    "source": "github"
  },
  "websiteUrl": "https://savantcat.cn/mcp/",
  "description": "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。"
}