Skip to main content
Glama
savantcat

savantcat-ai-compliance-mcp

Official
by savantcat
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault

No arguments

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_topicsA

列出全部合规条目的标题清单。

Args:
    cluster: 可选，按集群过滤。可选值 genai-interim(生成式AI暂行办法) /
             ai-content-label(AI生成合成内容标识) / deep-synthesis(深度合成) /
             algo-recommendation(算法推荐与备案) / filing-practice(备案实操)
search_complianceA

按关键词检索中国 AI 合规条目，返回最相关的若干条（含结论与条文依据）。

Args:
    query: 检索词，如「AI 客服 备案」「AI 生成内容 标注」「训练数据 合法来源」「大数据杀熟」
    top_k: 返回条数，默认 5
get_requirementA

按 slug 取一条合规要求的完整内容（正文 + 依据条文 + 落地动作 + 常见追问）。

Args:
    slug: 条目标识，先用 list_topics 或 search_compliance 取得
self_checkA

按场景出合规自查清单：把命中条目的「落地动作」汇总成可勾选待办，并列出条文依据。

Args:
    scope: 场景或关键词，如「AI 客服」「营销文案 标注」「小程序 上架」「全量」；
           留空则返回全量自查清单
filing_routeA

判断一项 AI 服务要办哪些手续（备案/安全评估/标识），逐条给出法规依据。

Args:
    public_facing: 是否面向中国境内公众提供服务（仅内部使用请传 false）
    generates_content: 是否能生成文本/图片/音频/视频等内容
    edits_face_or_voice: 是否提供人脸、人声等生物识别信息编辑功能（换脸、AI 配音、数字人）
    only_internal_use: 是否仅企业内部使用、不对外提供
regulation_infoA

获取收录法规清单（名称、发布/施行日期、条数、官方原文链接、核心要求）。

get_articleA

按条号取某部法规的条文逐字原文，并附内容指纹与官方原文链接。

与 get_requirement 的分工：get_requirement 按「问题」取整条合规要求（含结论与落地动作）；
get_article 按「条号」取条文原文，用于逐字核对、引用与溯源。

Args:
    law: 法规名或集群标识。可写全称（《生成式人工智能服务管理暂行办法》）、
         简称（标识办法 / 算法推荐规定）或 cluster
         （genai-interim / ai-content-label / deep-synthesis / algo-recommendation）
    article: 条号，支持「第十条」「10」「第10条」三种写法
search_articlesA

在某一部法规内部按关键词检索条文，返回命中条号 + 条文摘录。

用途：已经知道是哪部法规，要定位「哪一条讲了这件事」。

Args:
    law: 法规名或集群标识（同 get_article 的 law 参数）
    keywords: 检索词，如「训练数据 合法来源」「标识 元数据」「备案 十日」
    top_k: 返回条数，默认 5

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.9/5.0

Scored across 8 tools

Disambiguation4/5

Descriptions explicitly delineate the trickiest pair (get_requirement by problem vs get_article by article number), and search_articles (within one law) vs search_compliance (across all entries) is spelled out. The remaining border pair list_topics vs regulation_info (entries vs regulations) is separable but subtler, so a minor confusion risk remains.

Naming Consistency3/5

All names are snake_case and readable, but only five of eight follow a clear verb_noun pattern (get_requirement, get_article, search_articles, list_topics, search_compliance). filing_route, regulation_info, and self_check break the verb-first convention, giving a mixed but still legible scheme.

Tool Count5/5

Eight tools is well-scoped for a regulatory lookup/reference server, with each tool occupying a distinct retrieval niche (per-entry, per-article, per-law search, cross-entry search, filing decision, scenario checklist). No obvious redundancy or padding.

Completeness4/5

The surface covers the retrieval lifecycle well: browse (list_topics, regulation_info), locate (search_compliance, search_articles), fetch verbatim (get_article, get_requirement), and apply (filing_route, self_check). Minor gaps exist, such as no explicit cross-regulation comparison or update/version-delta lookup, but core workflows are covered.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources