HimiTrace MCP Server
A Model Context Protocol (MCP) server connecting AI agents to the Polygon blockchain for product origin verification and supply chain timeline auditing
README
HimiTrace MCP Server — Blockchain Product Traceability for AI Agents
HimiTrace is a Model Context Protocol (MCP) server that connects AI agents directly to the Polygon Mainnet blockchain to check product authenticity, verify origins, and inspect supply chain event lineages. Developed by HimiTek (himitek.com), it bridges immutable on-chain trust data with natural language queries for AI agents.
This allows any MCP-compatible AI agent (such as Claude Desktop, Cursor, Windsurf, or ChatGPT) to seamlessly query, track, and audit physical goods (such as Vietnamese agricultural exports, seafood, and components) on-chain in plain language.
Key Features
- On-Chain Verification: Verify if a product or batch ID is registered on the Polygon blockchain (tamper-proof, immutable).
- Supply Chain Timeline (GS1 EPCIS compatible): Retrieve the full chronological event log of a product (harvesting, processing, packaging, shipping) directly from Polygon.
- Certificate Verification: Access quality certificates (USDA Organic, VietGAP, Fair Trade, etc.) stored on IPFS with their hashes anchored on-chain.
- BOM (Bill of Materials) Lineage: Trace parent-child merge/split relationships of raw material batches.
- Zero Gas Cost: All read operations from the smart contract are 100% free and do not require any crypto tokens (POL) to be spent by the AI agent.
Technical Specifications
- Contract Address:
0xFF7A3429427aFda56b2994B2F3eeF4464b851EE0 - Network: Polygon Mainnet (Chain ID:
137) - Framework: built on Anthropic's Model Context Protocol (MCP) using Python
FastMCP.
Installation & Setup
1. Prerequisites
- Python 3.10 or higher
- Access to a Polygon RPC node (default public RPCs are configured, or you can specify your own).
2. Install Dependencies
Clone the repository and install the required packages:
pip install -r requirements.txt
3. Test Connection
Ensure that the server can connect to the Polygon contract and query tools locally:
python test_local.py
If you see ALL TESTS PASSED, your environment is configured correctly.
Connecting to AI Clients
1. Claude Desktop
Add HimiTrace MCP to your Claude Desktop configuration file.
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
Add the following to the mcpServers object:
{
"mcpServers": {
"himitrace": {
"command": "python",
"args": [
"C:/path/to/your/himitrace/mcp_server/server.py"
]
}
}
}
Note: Make sure to replace C:/path/to/your/himitrace/mcp_server/server.py with the actual absolute path to your server.py.
2. Cursor or Windsurf IDE
In Cursor settings:
- Go to Settings > Features > MCP.
- Click + Add New MCP Server.
- Fill in the fields:
- Name:
HimiTrace - Type:
command - Command:
python "C:/path/to/your/himitrace/mcp_server/server.py"
- Name:
Available Tools
AI agents can execute the following tools:
1. verify_product
Checks if a product exists on-chain and retrieves its registration parameters.
- Argument:
product_id(string, e.g.,LOT-20260315-A1B2C3) - Returns: JSON containing verification status, name, origin, owner, registration date, and explorer links.
2. get_trace_history
Retrieves the complete supply chain history (timeline) of a product.
- Argument:
product_id(string) - Returns: Chronological array of events, including event types, timestamps, custom payload data (GS1 EPCIS standard), and the recorder's blockchain wallet address.
3. get_certificates
Retrieves certificates attached to a product.
- Argument:
product_id(string) - Returns: Lists certificate types, issuers, dates of issue/expiration, and secure IPFS gateway links.
4. get_batch_lineage
Traces the Bill of Materials (BOM) lineage (splits and merges of batches).
- Argument:
batch_id(string) - Returns: Parent-child relationships, quantities, and units of raw material inputs.
5. check_product_exists
Quick check for product presence.
- Argument:
product_id(string) - Returns: True/False status.
6. get_system_stats
Provides overall system statistics.
- Returns: Registered products count, contract details, and wallet balance.
Available Resources
AI agents can reference the following static resources:
himitrace://info: General system documentation, compliant industries, and standards.himitrace://contract: Blockchain metadata (chain_id, RPC node, contract code version).himitrace://pricing: Pricing tiers for API limits (Free, Pro, Enterprise).
Production Deployment (HTTP / SSE mode)
To run HimiTrace MCP in Server-Sent Events (SSE) mode over HTTP for remote AI integrations:
fastmcp run server.py --transport sse --port 8900
This starts an SSE server on port 8900 which can be exposed securely via reverse proxy (e.g., Nginx with TLS) or tools like Ngrok/Cloudflare Tunnels.
License & Support
Developed and maintained by HimiTek Joint Stock Company.
- Website: himitek.com
- Support Email: mcp@himitek.com
- Portal: trace.himitek.vn
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.