Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
SSH, files, containers and databases via the OpsMaxx desktop app - scoped per capability, audited.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
OPSMAXX_MCP_TOKEN, OPSMAXX_MCP_PORTValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"opsmaxx": {
"command": "npx",
"args": [
"-y",
"@opsmaxx/mcp"
],
"env": {
"OPSMAXX_MCP_TOKEN": "your-value",
"OPSMAXX_MCP_PORT": "your-value"
}
}
}
}Run this in your terminal
claude mcp add opsmaxx --env OPSMAXX_MCP_TOKEN=your-value --env OPSMAXX_MCP_PORT=your-value -- npx -y @opsmaxx/mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"opsmaxx": {
"command": "npx",
"args": [
"-y",
"@opsmaxx/mcp"
],
"env": {
"OPSMAXX_MCP_TOKEN": "your-value",
"OPSMAXX_MCP_PORT": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"opsmaxx": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@opsmaxx/mcp"
],
"env": {
"OPSMAXX_MCP_TOKEN": "your-value",
"OPSMAXX_MCP_PORT": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
OPSMAXX_MCP_PORT envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account OpsMaxx, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: OPSMAXX_MCP_TOKEN
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.3) reached the registry 2 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, AI Deprecations
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
AI model shutdown dates, replacements, change feed and webhook alerts for 8 providers.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Connect any stdio MCP client to a running OpsMaxx desktop app.
npx -y @opsmaxx/mcp
OpsMaxx already exposes an MCP server over Streamable HTTP on 127.0.0.1, and clients that can express an HTTP server with an Authorization header — Claude Code, Codex — should use that directly. It is one command:
opsmaxx claude
Some clients cannot. Claude Desktop, notably, does not read url or headers from claude_desktop_config.json at all, so an HTTP MCP server is simply not expressible there. This package is the adapter for those: stdio in, authenticated HTTP out.
It is a protocol relay. Every message is forwarded unmodified in both directions. No tool, session or policy logic lives here — access groups, approvals, secret redaction and the audit log all stay in the app, so a stdio client gets exactly the same treatment an HTTP client would.
It talks only to 127.0.0.1. It is not a server, it holds no state, and it cannot reach anything OpsMaxx would not already allow.
OpsMaxx must be running, with the bridge enabled under AI & MCP.
Environment first, then the session the opsmaxx CLI has already cached:
| Variable | Meaning |
|---|---|
OPSMAXX_MCP_TOKEN | Session token from AI & MCP → AI Agents → New AI agent session |
OPSMAXX_MCP_PORT | Bridge port, shown under AI & MCP → Security |
OPSMAXX_MCP_URL | Full endpoint instead of the port, e.g. http://127.0.0.1:5177/mcp |
If none are set it reads the session cached by the CLI, so running opsmaxx claude once is enough and there is no token to paste.
{
"mcpServers": { "opsmaxx": { "command": "npx", "args": ["-y", "@opsmaxx/mcp"], "env": { "OPSMAXX_MCP_TOKEN": "your-session-token", "OPSMAXX_MCP_PORT": "5177" } } } }
Restart Claude Desktop afterwards.
The token is scoped to one workspace and one access group, and it is the same secret you would otherwise paste into a client's config by hand. It is not an SSH key and it is not a vault password: an agent holding it still never receives an SSH password, a private key, a database credential, a hostname or an interactive root shell. See the threat model.
MIT. Source: https://github.com/OpsMaxx/OpsMaxx