Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Hosted remote MCP for protected account access, permissions, activity history and supported undo.
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.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://secure.lea.sh/mcpRun this in your terminal
claude mcp add --transport http leash https://secure.lea.sh/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"leash": {
"url": "https://secure.lea.sh/mcp"
}
}
}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": {
"leash": {
"type": "http",
"url": "https://secure.lea.sh/mcp"
}
}
}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.
ChatGPT connects only to servers on the internet:
https://secure.lea.sh/mcpMenu names can differ slightly by plan and over time.
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.
The server asks you to sign in before it lists its tools.
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 open-leash, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 437 ms (HTTP 401)
Declares OAuth sign-in, so your AI app can take you to log in
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 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 in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.2) reached the registry 4 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, Georgia MCP
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.
An MCP server for Georgian public data, read from the organizations that publish it.
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.
A little peace of mind for your AI. Free.
Leash connects your AI to your accounts through configurable protections. Review activity, control each AI's access, and undo supported reversible actions when undo is enabled. Only activity routed through Leash is covered.
Install Leash from your AI's plugin directory when its listing is available, or install this package from GitHub in clients that support repository plugins. Enable the Leash connection and sign in at openleash.com when prompted. Each installation receives a separate, revocable connection. Some hosts share one connection across multiple bots; Leash cannot distinguish bots that use the same credentials. Use separate connections where your host supports them. The shared endpoint is https://secure.openleash.com/mcp. Never append another person's token or put a personal link in a public package.
For Gemini CLI: gemini extensions install https://github.com/open-leash/leash-plugin. Run /mcp auth leash if sign-in is requested. For OpenClaw, use openclaw plugins install git:github.com/open-leash/leash-plugin@v1.0.3, then inspect the enabled leash bundle. Its compatibility format is Cursor; no native code runs. For other clients, use their remote HTTP server option with the shared endpoint and OAuth. A public directory submission is not the same as an approved listing. Check the release notes for current availability.
Run the Leash setup skill or ask: "Check Leash is connected without accessing my personal accounts." Success must come from the check_connection tool, not merely from listing available tools. Then connect the accounts you want at https://openleash.com/personal.
This package includes a setup skill and a personal-account skill. Cursor loads a packaged rule and Gemini CLI loads GEMINI.md while the extension is enabled. A plugin cannot guarantee that all AI activity uses Leash. For a permanent preference in other clients, add the credential-free rule from GEMINI.md to the client's supported personal instructions. ChatGPT web uses Settings → Personalization → Custom instructions; Claude app uses Settings → General → Instructions for Claude; Cursor uses User Rules. A chat reply confirming the connection does not confirm that these settings were saved. Preserve your other instructions. Never add credentials to memory or shared files.
This integration uses personal Leash connections. The personal-connection retention terms apply to it; workspace and desktop-client retention terms describe the separate business service. Protection checks may process relevant request and response content with TypeSafe JEV. Audit history is retained for 90 days. When undo is enabled, supported recovery details are encrypted and retained for up to 7 days. Turning undo off stops new recovery capture. Read https://openleash.com/privacy for the full policy.
Disable or uninstall the plugin in your AI, remove any Leash-specific saved preference you added, then remove its connection in Your AIs at https://openleash.com/personal. Removing that connection revokes access immediately without disconnecting other AIs.
https://openleash.com/contact · max@openleash.com
Privacy: https://openleash.com/privacy · Terms: https://openleash.com/terms
This repository contains only public integration metadata, instructions and brand assets. Leash's gateway and protection engine remain private.