Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
SCADA station on your computer that an AI assistant reads, configures and operates over MCP.
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.
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Download the maker’s .mcpb file
The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.
Run this in your terminal
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.
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.
These 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 7, 2026
The registry name was verified with the GitHub account ganterlab, 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.
The registry does not list a required key, though some servers ask you to sign in on first use.
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 (1.0.3) reached the registry 22 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Signoff
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.
Five gates that make an agent's 'done' provable: run them, read the verdict, audit the record.
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 Claude, Codex or any assistant with MCP to Ganter Lab, the SCADA station that runs on your computer. The assistant reads live values and history, configures devices, logic and screens, and operates only the areas the station allows.
Ganter Lab must be installed and running on the same computer. This repository holds only the pieces an assistant uses to reach it: the Claude Desktop bundle, the Claude Code plugin and the registry entries. Ganter Lab itself is downloaded from ganterlab.com.
Ganter Lab is a SCADA station for Windows: it talks to PLCs, meters and sensors over Modbus, OPC UA, Siemens S7, MQTT and other drivers, keeps their history, raises alarms and draws operation screens. Its built-in MCP server lets an assistant work on that station:
Nothing leaves the computer. The server listens on the loopback interface only (http://127.0.0.1:18181/mcp, Streamable HTTP) and exists only while the station runs. The station's Agent page decides, area by area behind a master switch, what an assistant may read, configure or operate, and every change an assistant makes is written to the station's event journal under its own name.
http://127.0.0.1:18181/mcp; the port is the page's Port field.Download ganter-lab.mcpb from the latest release and open it: Claude Desktop shows its install dialog. If the station's port is not 18181, set the MCP endpoint field to the address the Agent page shows. The Node runtime the bundle needs comes with Claude Desktop. The station's Agent page offers the bundle too (Install in Claude Desktop).
Through the plugin in this repository:
claude plugin marketplace add ganterlab/ganter-lab-mcp
claude plugin install ganter-lab@ganter-lab
Or with one command and no plugin:
claude mcp add --transport http ganterlab http://127.0.0.1:18181/mcp
Another port. The plugin's MCP endpoint setting holds the station's address, filled in with the default, http://127.0.0.1:18181/mcp. If the Agent page shows another port, change that setting to the address the page shows: Claude Code asks for it when the plugin is enabled, and /config lists it afterwards.
Add the station to ~/.codex/config.toml:
[mcp_servers.ganterlab]
url = "http://127.0.0.1:18181/mcp"
Any client running on the same computer that takes a Streamable HTTP server address connects to http://127.0.0.1:18181/mcp (the port is the one the Agent page shows). Clients that reach servers from the internet, such as ChatGPT connectors or the Gemini web chat, are not supported: the station listens on this computer only.
The assistant guide covers every client and every area: www.ganterlab.com/en/docs/agent.
| File | What it is |
|---|---|
bridge.mjs | The Claude Desktop bundle's bridge: it speaks MCP over stdio to Claude Desktop and forwards each message to the station's endpoint. Built-in Node only, no dependencies. When the station restarts (an update relaunches it), the bridge opens a new session and replays the call, so Claude Desktop needs no restart. For debugging it runs alone: node bridge.mjs http://127.0.0.1:18181/mcp |
manifest.json, icon.png | The bundle's manifest and mark. With bridge.mjs they make ganter-lab.mcpb, attached to each release |
plugin/ | The Claude Code plugin, in a folder of its own: what Claude Code installs and Anthropic's directory lists |
.claude-plugin/marketplace.json | The plugin marketplace of this repository, which points Claude Code at plugin/ |
server.json | The entry in the official MCP Registry, io.github.ganterlab/ganter-lab |
glama.json | The maintainers, for Glama |
.github/workflows/publish-registry.yml | Publishes server.json to the MCP Registry from GitHub Actions, run by hand after a release |
This package has a version number of its own, which changes only when the bridge, the manifest or the plugin changes, not with every version of Ganter Lab.
Ganter Lab's plans are on the pricing page.
Questions and problems: contact@ganterlab.com. Security reports go to the same address.
The bridge, the manifest and the plugin are under the MIT License. Ganter Lab itself is commercial software and is not in this repository; the Ganter Lab name and mark are not licensed by it.