Commerce Operations Foundation MCP server
Commit Sep 3, 2026Enables AI agents to manage orders, inventory, and fulfillment through a standardized interface using the Order Network eXchange Standard.
Also known as commerce-operations-foundation/mcp-reference-server
- Stars
- 38
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Sep 3, 2026
- License
- MIT
What is Commerce Operations Foundation MCP?
Commerce Operations Foundation enables AI agents to manage orders, inventory, and fulfillment through a standardized interface using the Order Network eXchange Standard.
Summary generated from the project's README
About Commerce Operations Foundation MCP server
Managing commerce operations like order capture and delivery through AI agents is the core capability provided to developers. It implements the Order Network eXchange Standard to provide a bridge between AI assistants such as Claude and various fulfillment backends. Developers can use it locally via stdio transport by running the server with node after installing dependencies through npm.
The system provides twelve standardized operations divided into five action tools and seven query tools. Users can execute commands like create-sales-order, cancel-order, and fulfill-order, or retrieve data using get-inventory, get-customers, and get-products. While it includes a built-in mock adapter for testing, retailers can deploy it with custom adapters by configuring environment variables such as ADAPTER_TYPE and ADAPTER_PATH. This setup allows for a unified way to handle product catalogs, customer information, and shipment tracking.
What you can do with it
- 1Managing customer ordersAn AI agent can create or modify sales orders and handle cancellations.
- 2Checking product availabilityA developer can use an AI to verify current inventory levels.
- 3Tracking shipment progressAn AI assistant can monitor the status of various fulfillments.
- 4Handling item returnsThe server allows an AI to initiate returns and track exchange details.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablecommerce-operations-foundation/mcp-reference-server is public and reachablegithub.com/commerce-operations-foundation/mcp-reference-serv ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-09-03github.com/commerce-operations-foundation/mcp-reference-serv ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubCommerce Operations Foundation MCP Server
Universal Fulfillment System for the AI Era
The Commerce Operations Foundation MCP Server implements the Order Network eXchange Standard (onX), providing a standardized interface between AI agents and fulfillment systems through the Model Context Protocol (MCP).
This project enables AI assistants like Claude to seamlessly interact with any fulfillment system, streamlining commerce operations from order capture through delivery.
Project Purpose
- Standardize Fulfillment Integration: Define a universal protocol for fulfillment operations
- Enable AI-Driven Commerce: Allow AI agents to manage orders, inventory, and fulfillment
- Simplify Implementation: Provide plug-and-play adapters for different Fulfillment backends
- Accelerate Innovation: Create a foundation for next-generation commerce automation
Project Structure
/server
The core Fulfillment MCP Reference server implementation that:
- Handles MCP protocol communication (stdio transport)
- Routes requests to appropriate adapters
- Provides 12 standardized fulfillment operations (5 action + 7 query tools)
- Includes a built-in mock adapter for testing
/adapter-template
Template for creating custom Fulfillment adapters to allow the MCP Reference server to connect to your Fulfillment system:
- Boilerplate code for new integrations
- TypeScript interfaces and types
- Testing framework setup
- Publishing guidelines for vendors
/docs
Comprehensive documentation covering:
- Order Network eXchange specification and standards
- Architecture and design decisions
- Integration guides for different stakeholders
- API reference and examples
/schemas
JSON Schema definitions for:
- Order data structures
- Customer information
- Product catalog
- Inventory models
Quick Start
For AI Developers
Integrate order management capabilities into your AI applications:
git clone https://github.com/commerce-operations-foundation/mcp-reference-server.git
cd mcp-reference-server/server
npm install
npm run build
node dist/index.js
The server uses the mock adapter by default (ADAPTER_TYPE=built-in, ADAPTER_NAME=mock). Configure your AI platform (like Claude Desktop) to execute node /absolute/path/to/server/dist/index.js. See the Installation Guide for platform-specific setup.
For Fulfillment Vendors
Create an adapter for your fulfillment system:
# Copy the adapter template
cp -r adapter-template your-fulfillment-adapter
cd your-fulfillment-adapter
# Install dependencies and start developing
npm install
npm run dev
For Retailers & Commerce Platforms
Deploy the server with your chosen adapter:
git clone https://github.com/commerce-operations-foundation/mcp-reference-server.git
cd mcp-reference-server/server
npm install
cp .env.example .env
# edit .env and set ADAPTER_TYPE/ADAPTER_PACKAGE/ADAPTER_PATH as needed
npm run build
npm start
Core Capabilities
The server provides 12 essential fulfillment operations:
Action Tools
create-sales-order- Create new orders from any channelupdate-order- Modify order details and line itemscancel-order- Cancel orders with reason trackingfulfill-order- Mark orders as fulfilled and return shipment detailscreate-return- Create returns for order items with refund/exchange tracking
Query Tools
get-orders- Retrieve order informationget-customers- Get customer detailsget-products- Get product informationget-product-variants- Retrieve variant-level dataget-inventory- Check inventory levelsget-fulfillments- Track fulfillment statusget-returns- Query return records and status
Architecture Overview
┌──────────────┐ ┌────────────────┐ ┌──────────────────┐
│ AI Platform │────▶│ MCP Server │────▶│ Fulfillment │
│ (Claude) │ │ (This Project) │ │ Adapter │
└──────────────┘ └────────────────┘ └──────────────────┘
│ │
▼ ▼
┌─────────┐ ┌──────────┐
│ Schemas │ │Fulfillment│
│ (JSON) │ │ Backend │
└─────────┘ └──────────┘
Testing
The project includes comprehensive testing at all levels:
# Run all tests
cd server
npm test
# Run specific test suites
npm run test:unit # Unit tests
npm run test:integration # Integration tests
# Test with coverage
npm run test:coverage
Documentation
Documentation is available in the following locations:
- Full Documentation - Complete specification and guides
- Server README - Detailed server implementation
- Adapter Template - Creating custom adapters
- Architecture Overview - System design and components
Contributing
We welcome contributions from the community! Whether you're:
- A Fulfillment vendor creating an adapter
- A developer improving the core server
- A user reporting issues or suggesting features
Please open an issue or pull request to get started.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Resources
- Model Context Protocol - The foundation protocol
- Installation Guide - Detailed setup instructions
- Configuration Guide - All configuration options
- Example Test Prompts - Common use cases and testing scenarios
Get Started
Ready to revolutionize your fulfillment operations with AI?
- Fulfillment Vendors: Create your adapter
- AI Developers: Integrate the server
- Commerce Teams: Deploy the solution with Docker or your preferred runtime
Together, we're building the foundation for AI-powered commerce operations.
Commerce Operations Foundation MCP questions
What operations does the server support?
The server provides 12 essential fulfillment operations, consisting of 5 action tools and 7 query tools.
How can I connect my own fulfillment system to the server?
You can use the provided adapter template to create custom integrations for your specific fulfillment backend.
Is there a way to test the server without a real backend?
Yes, the implementation includes a built-in mock adapter specifically for testing.