Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"Apache OFBiz": {
"args": [
"-y",
"mcp-remote",
"http://localhost:3000/mcp",
"--allow-http"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
This project provides an implementation of a Model Context Protocol (MCP) server that runs custom tools to invoke remote services thorugh API endpoints, based on requests from an MCP client (usually hosted in a generative AI application such as Claude Desktop).
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y 'mcp-server' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked mcp-server against OSV.dev.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in ecommerce
Production-grade MCP server and CLI tool for Shopify Admin GraphQL API — 49+ tools, YAML-extensible, dual auth, dual transport, Docker-ready
A command line tool for setting up commercetools MCP server
35+ AI tools for TCG card grading, Monte Carlo pricing, 370K+ product search. BYOK.
This is the reference implementation for the mcp server
MCP Security Weekly
Get CVE alerts and security updates for Mcp Server For Apache Ofbiz and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
This project provides an implementation of a Model Context Protocol (MCP) server that runs custom tools to invoke remote services thorugh API endpoints, based on requests from an MCP client (usually hosted in a generative AI application such as Claude Desktop).
The project is implemented with the Anthropic TypeScript SDK, and requires Node.js as runtime environment.
By leveraging the sample configuration and tool files contained in the examples folder, the MCP server can be easly configured, e.g., to point to specific backend systems and to use OAuth2.0 authorization flows, and new tools can be developed to address specific use cases.
In short, this project can be used as a platform to implement your own tools and enable generative AI applications to interact with any backend system that exposes API endpoints, such as Apache OFBiz® or Moqui.
This software is licensed under the Apache License, Version 2.0.
Apache OFBiz® is a trademark of the Apache Software Foundation.
> git clone https://github.com/jacopoc/mcp-server-for-apache-ofbiz.git mcp-server
> cd mcp-server
mcp-server> npm install
mcp-server> cd examples/tools
mcp-server/examples/tools> npm install
mcp-server/examples/tools> npm run build
mcp-server/examples/tools> cd ..
mcp-server/examples> ./update_token.sh admin ofbiz
mcp-server/examples> cd ..
mcp-server> node build/server.js ./examples/config ./examples/tools
From another shell you can start the MCP Inspector:
> npx @modelcontextprotocol/inspector
This command will open a browser window to the Inspector application: set Transport Type to Streamable HTTP and URL to http://localhost:3000/mcp and hit the Connect button. After that, you will be connected to the MCP server and could execute its tool, that fetches data from one of the public demo instances of Apache OFBiz.
The MCP server communicates with the MCP client via MCP Streamable HTTP transport.
The server dynamically discovers custom tools contained in a directory, whose path is specified as a command-line argument when the server is lauched.
The tools are defined and implemented in their own files. For example, the sample tool examples/tools/src/findProductById.ts invokes an endpoint in Apache OFBiz to retrieve product information for a given product ID. This works with an out-of-the-box (OOTB) OFBiz instance with the rest-api plugin installed.
The server:
Server configuration is managed via the config.json file contained in a configuration directory, whose path is specified as a command-line argument when the server is l