{
"mcpServers": {
"zopen-mcp-server": {
"command": "<see-readme>",
"args": []
}
}
}No install config available. Check the server's README for setup instructions.
Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
An MCP server for zopen
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
License not specified.
Is it maintained?
Last commit 37 days ago. 1 stars.
Will it work with my client?
Transport: stdio. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
No automated test available for this server. Check the GitHub README for setup instructions.
No known vulnerabilities.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationHave you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Persistent memory using a knowledge graph
Privacy-first. MCP is the protocol for tool access. We're the virtualization layer for context.
Pre-build reality check. Scans GitHub, HN, npm, PyPI, Product Hunt — returns 0-100 signal.
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
MCP Security Weekly
Get CVE alerts and security updates for Zopen Mcp Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
zopen-mcp-server is a Go-based Model Context Protocol (MCP) server that provides AI assistants with access to zopen and zopen-generate command-line tools for managing z/OS packages and porting open-source software to z/OS.
zopen commands on a remote z/OS system via SSHzopen and zopen-generate commands on your local machineBy default, zopen-mcp-server communicates over stdio (standard input/output). When launched by a parent application, this creates a direct and isolated communication channel. This method is inherently secure because the server is not exposed to a network port, preventing any unauthorized external connections.
When running in remote mode, the server uses SSH to execute commands on the target z/OS system. All actions are performed with the permissions of the SSH user provided. It is crucial to use an SSH key with the appropriate level of authority for the tasks you intend to perform.
go install (Recommended)go install github.com/zopencommunity/zopen-mcp-server@latest
This will install the zopen-mcp-server binary to your $GOPATH/bin directory (typically ~/go/bin).
# Clone the repository
git clone https://github.com/zopencommunity/zopen-mcp-server.git
cd zopen-mcp-server
# Build using make
make build
# Or build directly with go
go build -o zopen-mcp-server zopen-server.go
zopen installed (either locally or on a remote z/OS system)zopen-generate installed and accessible in the PATH{
"mcpServers": {
"zopen": {
"command": "zopen-mcp-server",
"args": []
}
}
}
If you installed with go install, make sure ~/go/bin is in your PATH. Alternatively, use the full path:
{
"mcpServers": {
"zopen": {
"command": "/Users/yourname/go/bin/zopen-mcp-server",
"args": []
}
}
}
{
"mcpServers": {
"zopen": {
"command": "zopen-mcp-server",
"args": [
"--remote",
"--host", "your-zos-hostname",
"--user", "your-username",
"--key", "/path/to/your/ssh/key"
]
}
}
}
{
"mcpServers": {
"zopen": {
"command": "zopen-mcp-server",
"args": [],
"env": {
"DEBUG": "1"
}
}
}
}
After updating the configuration, restart the AI agent Desktop for the changes to take effect.
To provide the AI agent with detailed instructions on z/OS porting workflows, add the AGENTS.md file to the context in your settings:
{
"mcpServers": {
"zopen": {
"command": "/home/itodoro/go/bin/zopen-mcp-server",
"args": []
}
},
"context": {
"fileName": ["AGENTS.md"]
}
}
The AGENTS.md file contains comprehensive guidance for AI agents on how to port software to z/OS, including common issues, best practices, and workflow steps.
Once configured, the AI agent will have access to all zopen tools. You can ask it to:
Here are some example requests you can make to the AI agent: