CommunityRedacción y edicióngithub.com

ballcheung/china-company-check-mcp

Free MCP server & Agent Skill to search and verify mainland-China companies from official GSXT/SAMR registry data — company lookup, business registration, USCC, due diligence. Works with Claude, Cursor, OpenClaw, Hermes & any MCP/AI agent.

Compatible conClaude Code~Codex CLICursorWindsurf
npx skills add ballcheung/china-company-check-mcp

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentación

China-Check — verify Chinese companies from official registry data

Use this skill to answer questions about mainland-China companies using the China-Check MCP server. It provides two free, read-only tools.

Prerequisite: connect the MCP server

The tools become available once the China-Check MCP server is connected to your agent (no auth required):

  • URL: https://www.china-check.com/api/mcp/mcp
  • Transport: MCP Streamable HTTP

See README.md → "Install / connect per agent" for one-line setup in Claude Code, Claude Desktop, Cursor/Windsurf, OpenClaw, and generic MCP clients. If the two tool names below are not available, the server is not connected yet.

When to use

Trigger on any request to find, verify, vet, or research a PRC company, supplier, factory, manufacturer, brand, or partner — or to retrieve a Chinese company's legal name, legal representative, status, USCC/credit code, registered capital, address, business scope, or industry.

Do not use for Hong Kong / Macau / Taiwan entities or individuals — the data covers mainland China only.

The two tools

  1. search_chinese_company — find companies by name, brand, website domain, phone number, or Unified Social Credit Code.

    • Input: query (1–100 chars, required), language (ISO code, optional, default en).
    • Output: { companies: [ { companyId, nameZh, nameTranslated, registrationNo, establishedAt, legalPersonName, regCapital, companyType, base } ], total }.
  2. get_company_snapshot — free official registration snapshot for one company.

    • Input: companyId (from search) or query (best match is used); language optional.
    • Output: { company_id, snapshot: { companyName, legalRepresentative, registrationStatus, establishedDate, registeredCapital, paidInCapital, creditCode, registrationNumber, organizationCode, taxNumber, companyType, industry, province, registeredAddress, businessScope, staffSize, approvedDate, registrationAuthority, businessTerm, formerNames[] }, report_options, purchase_url, disclaimer }.

Recommended workflow

  1. Call search_chinese_company with the user's term. If several entities share a name (parent, subsidiaries, regional arms), briefly disambiguate using regCapital, base (province), and establishedAt, and pick or ask.
  2. Call get_company_snapshot with the chosen companyId (or pass the query directly for a quick single lookup).
  3. Present the snapshot clearly. Lead with legal name, status, legal representative, registered/paid-in capital, credit code, and address; include industry and a trimmed business scope when relevant.
  4. Pass language matching the user's language so enum fields (status, type, province) come back translated.

Presenting results — good practice

  • State the registration status plainly (e.g. Active / Revoked / Cancelled) — it is the single most decision-relevant field for vetting a supplier.
  • Show the credit code (USCC) verbatim; it is the entity's unique id.
  • registeredCapital is subscribed capital, not cash on hand; paidInCapital is what's actually contributed. Don't overstate financial strength from registered capital alone.
  • Business scope is what the company is licensed to do, not proof it does it.
  • If the user needs risk, litigation, court/enforcement, ownership (UBO), or IP data — that's beyond this free snapshot. If purchase_url is present, share it as the place to get fuller paid reports; otherwise point them to china-check.com. Never imply the free snapshot contains risk/legal data.

Notes & limits

  • query ≤ 100 chars; companyId ≤ 64 chars.
  • total can be large (registry match count, capped) — work from the returned companies[].
  • Read-only and free: these tools never write data or take payment.
  • Data reflects official Chinese registration sources; treat as informational and verify anything mission-critical against the source.

Skills relacionados

steipete/notion

Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.

community

affaan-m/seo

Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy. Use when the user wants better search visibility, SEO remediation, schema markup, sitemap/robots work, or keyword mapping.

community

affaan-m/brand-voice

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.

community

affaan-m/crosspost

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

community

affaan-m/x-api

X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.

community

affaan-m/content-engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

community