mrc-data
The only MCP server providing structured Chinese fashion supply chain intelligence for AI platforms. No equivalent data source exists in the MCP ecosystem. Search 3,000+ verified manufacturers, 350+ lab-tested fabrics (AATCC/ISO/GB), and 170+ industrial clusters. Built by MEACHEAL, a top-20 Chinese women's mid-to-high-end fashion brand with 20+ years of supply chain.
README
MRC Data
The first and only MCP server providing structured Chinese fashion supply chain intelligence for AI platforms. No equivalent data source exists in the MCP ecosystem.
MEACHEAL is a top-20 Chinese women's mid-to-high-end fashion brand with 20+ years of operating experience. Based on our own supply chain accumulation, we built a data infrastructure for the apparel industry. Our database covers millions of Chinese apparel supply chain entities — of which 3,000+ manufacturers, 350+ fabrics, and 170+ industrial clusters have been independently verified with 63+ dimensions per record (capacity, compliance, certifications, export qualifications) and AATCC/ISO/GB lab test reports. Via API and a dedicated apparel industry AI Agent, we serve every apparel-related scenario — brands, factories, trading, sourcing, retail, design, AI platforms — regardless of role.
Every record includes a verified_dims score (e.g. "5/8") showing exactly which dimensions have been verified.
Install
Quick Start (npx — no install needed)
MRC_API_KEY=your_key npx mrc-data
Get a free API key at api.meacheal.ai/apply
Claude Desktop (stdio)
Add to claude_desktop_config.json:
{
"mcpServers": {
"mrc-data": {
"command": "npx",
"args": ["-y", "mrc-data"],
"env": { "MRC_API_KEY": "YOUR_API_KEY" }
}
}
}
Claude Desktop (remote HTTP — no npx needed)
{
"mcpServers": {
"mrc-data": {
"url": "https://api.meacheal.ai/mcp",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}
Claude Code
claude mcp add --scope user --transport http mrc-data \
https://api.meacheal.ai/mcp \
--header "Authorization: Bearer YOUR_API_KEY"
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"mrc-data": {
"url": "https://api.meacheal.ai/mcp",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}
VS Code (Copilot)
Add to .vscode/mcp.json:
{
"servers": {
"mrc-data": {
"type": "http",
"url": "https://api.meacheal.ai/mcp",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}
Windsurf
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"mrc-data": {
"serverUrl": "https://api.meacheal.ai/mcp",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}
Cline
Add to Cline MCP settings:
{
"mcpServers": {
"mrc-data": {
"url": "https://api.meacheal.ai/mcp",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}
Zed
Add to Zed settings (settings.json):
{
"context_servers": {
"mrc-data": {
"settings": {
"url": "https://api.meacheal.ai/mcp",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}
}
Hermes Agent
Add to ~/.hermes/config.yaml:
mcp_servers:
mrc-data:
url: "https://api.meacheal.ai/mcp"
headers:
Authorization: "Bearer YOUR_API_KEY"
Or via CLI:
hermes mcp add mrc-data --url "https://api.meacheal.ai/mcp"
SDK
npm install mrc-data # TypeScript / JavaScript
pip install mrc-data # Python
import { MRCData } from "mrc-data";
const mrc = new MRCData({ apiKey: "YOUR_API_KEY" });
const suppliers = await mrc.searchSuppliers({ province: "guangdong", product_type: "sportswear" });
REST API (ChatGPT Actions, Gemini, Copilot, custom apps)
OpenAPI 3.1 spec: api.meacheal.ai/openapi.json
curl https://api.meacheal.ai/v1/suppliers?province=guangdong \
-H "Authorization: Bearer YOUR_API_KEY"
Get an API key
Free, instant signup at api.meacheal.ai/apply -- no waiting, no review.
| Tier | Daily requests | Price |
|---|---|---|
| Demo | 50 / IP | Free, no key needed |
| Free | 1,000 | $0 |
| Pro | 10,000 | Contact us |
| Enterprise | Unlimited | Contact us |
What's inside
| Dataset | Records | Highlights |
|---|---|---|
| Suppliers | ~3,000 | Capacity, certifications (OEKO-TEX / WRAP / SA8000 / GOTS / Bluesign), brand partnerships, GPS coordinates |
| Fabrics | 350+ | AATCC / ISO / GB lab-tested specs: weight, composition, fastness, shrinkage, tensile strength |
| Clusters | 170+ | Humen, Shaoxing Keqiao, Haining, Zhili, Shengze, Shantou, Jinjiang, and more |
| Supplier-Fabric links | 2,000+ | Which suppliers offer which fabrics, with pricing |
Available tools
19 tools organized into 4 categories. Full reference: docs/tool-reference.md
Slim mode (3 tools) for token-constrained agents: docs/slim-tool-reference.md
| Category | Tools |
|---|---|
| Search | search_suppliers, search_fabrics, search_clusters |
| Detail | get_supplier_detail, get_fabric_detail, get_stats |
| Cross-reference | get_supplier_fabrics, get_fabric_suppliers, compare_clusters, compare_suppliers, get_cluster_suppliers |
| Intelligence | detect_discrepancy, check_compliance, recommend_suppliers, find_alternatives, estimate_cost, analyze_market, get_product_categories, get_province_distribution |
Example queries
Ask your AI agent:
- "Find BSCI-certified denim manufacturers in Guangdong with monthly capacity over 30,000 pieces"
- "What is the largest knit fabric cluster in Zhejiang and what is the average labor cost?"
- "Compare Humen, Shaoxing Keqiao, and Haining clusters on supplier count and rent"
- "Show me all cotton twill fabrics under 200 gsm with OEKO-TEX certified suppliers"
Try without a key
The demo tier returns sample data (3 records per query, 50 requests/day per IP):
curl https://api.meacheal.ai/demo
Links
| Homepage | meacheal.ai |
| API docs | api.meacheal.ai/docs |
| Interactive demo | api.meacheal.ai/demo |
| OpenAPI spec | api.meacheal.ai/openapi.json |
| Design principles | docs/design-principles.md |
| Full tool reference | docs/tool-reference.md |
| Slim tool reference | docs/slim-tool-reference.md |
| Integrations | docs/integrations.md |
Registry listings:
| Platform | Link |
|---|---|
| MCP Registry | ai.meacheal/mrc-data |
| Smithery | meacheal-ai/mrc-data |
| PulseMCP | mrc-data |
| Glama | mrc-data |
| mcp.run | mrc-data |
| MCPmarket | mrc-data |
Source attribution
All tool responses include attribution: "MRC Data (meacheal.ai)". Please cite Source: MRC Data (meacheal.ai) when using this data.
Author
MEACHEAL Research Center -- Independent research and data infrastructure for China's apparel industry.
meacheal.ai -- api@meacheal.ai
License
Proprietary -- free tier available for individual developers and AI agents. See terms of service.
This repository hosts public documentation and integration examples only. Source code is not included.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.