Skip to content
MCP server

中国 AI 合规与备案(条文级自查)

Article-level answers on China's AI filing, labelling and algorithm rules, in Chinese

Install
Pricing
Open source
Platforms
API, CLI, self-hosted
Runs
Remotely
Version
1.1.1
Listing updated
1 day ago

About 中国 AI 合规与备案(条文级自查)

中国 AI 合规与备案(条文级自查) is an open-source MCP server for security. It runs as a hosted remote server, so there is nothing to install locally.

This server turns four Chinese AI regulations and one mandatory national standard into 42 article-level Q&As, each tied to the clause it comes from. Topics are generative AI interim measures (12 entries), labelling of AI-generated content (10), deep synthesis (8), algorithm recommendation and filing (8) and practical filing questions (4). Typical questions: whether an AI customer-service bot needs filing, whether building on a third-party model API leaves obligations with you, and how explicit and implicit labels differ.

Eight read-only tools cover it. list_topics browses entries, search_compliance returns an answer with its legal basis, get_requirement gives one entry in full, self_check builds a to-do list per scenario, and filing_route maps a service type to required actions. regulation_info lists the laws with dates and official links. get_article returns verbatim text by article number with a sha256 fingerprint and search_articles searches inside one regulation.

Sources are official publications and quotes are checked word for word at build time. The README states answers are a self-check reference, not legal advice, and filing practice depends on the local cyberspace authority. The code is Apache-2.0 and the hosted endpoint needs no key. It is run by SavantCat, a company that sells enterprise knowledge bases and AI customer service.

Install

Run in a terminal

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

Add to Settings → Connectors → Add custom connector

https://savantcat.cn/mcp-compliance
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "ai-compliance": {
      "url": "https://savantcat.cn/mcp-compliance"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "ai-compliance": {
      "type": "http",
      "url": "https://savantcat.cn/mcp-compliance"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "ai-compliance": {
      "serverUrl": "https://savantcat.cn/mcp-compliance"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "ai-compliance": {
      "type": "http",
      "url": "https://savantcat.cn/mcp-compliance"
    }
  }
}

Tools this server provides (8)

Taken from the project documentation; the running server may differ.

list_topics
List all entries, optionally filtered by group
search_compliance
Keyword search returning an answer with its legal basis
get_requirement
Get one entry in full with basis, actions and follow-up questions
self_check
Summarise a scenario into a self-check to-do list
filing_route
Map a service type to required actions with legal basis
regulation_info
List the covered regulations with dates, counts and official links
get_article
Get a regulation's verbatim article by number with a sha256 fingerprint
search_articles
Search for articles inside one regulation

What it does

42 clause-level answers
Q&As across five groups, each citing the regulation and article.
Verbatim article lookup
Fetch legal text by article number with a content fingerprint.
Filing route
Maps a service type to the filings and actions it needs.
Self-check list
Builds a compliance to-do list for a scenario.
Read-only tools
All eight tools only read data.
Local or hosted
Use the keyless endpoint or run the Python server yourself.

Good for

  • Check if a chatbot needs algorithm or generative AI filing
  • Work out how to label AI-generated images and video
  • Look up the exact text of an article in a regulation
  • Draft an internal compliance training outline

Pricing

Open source

Apache-2.0 code; free keyless hosted endpoint

Prices change. Check savantcat.cn before you buy.

中国 AI 合规与备案(条文级自查) FAQ

Is this legal advice?

No. The README says it is a self-check reference and filing requirements follow the local cyberspace authority.

Do I need an API key?

No, the hosted endpoint is keyless.

What languages does it use?

Content is in Chinese.

How many entries are there?

42 across five groups, based on four regulations and one mandatory standard.

Is 中国 AI 合规与备案(条文级自查) free?

Yes. 中国 AI 合规与备案(条文级自查) is open source, so you can use and self-host it for free.

How do I add 中国 AI 合规与备案(条文级自查) to Claude Code?

Run this command in your terminal: claude mcp add --transport http ai-compliance https://savantcat.cn/mcp-compliance

What are the best alternatives to 中国 AI 合规与备案(条文级自查)?

The closest alternatives to 中国 AI 合规与备案(条文级自查) are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.

Alternatives to 中国 AI 合规与备案(条文级自查)

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Agent Roast

    MCP server

    Offline review that flags agent changes which weaken tests, assertions or CI

    Runs locally
    • Open source
    • 4 Hacker News points
    • Developer tools
  3. Midplane

    MCP server

    Postgres gateway for AI agents with table grants, column masking and approval for writes

    Runs locally
    • Open source
    • 5 GitHub stars
    • Databases
  4. Leash

    MCP server

    Review what your AI touched, approve risky actions and undo supported changes

    • 1 tool
    • Remote
    • Free
    • 1 GitHub star
    • Security
  5. SecureCloud

    MCP server

    SentinelOne and IT security catalog, prices, quotes and checkout links for Israel

    • 7 tools
    • Remote
    • Free
    • Security