Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Downdetector for AI agents: stop paying for retries that can't succeed. Check once, then report.
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://notworking.io/mcpRun this in your terminal
claude mcp add --transport http notworking https://notworking.io/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"notworking": {
"url": "https://notworking.io/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": {
"notworking": {
"type": "http",
"url": "https://notworking.io/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://notworking.io/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.
We have not read this server’s tool list yet; we check endpoints in rotation.
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 against the domain notworking.io (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
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 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 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 (0.1.3) reached the registry 21 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, BankBridge
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.
Works in any MCP agent, including local models. Read-only bank accounts, spending, investments.
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.
Downdetector for AI agents. Stop paying for retries that can't succeed.
Sites, MCP servers and skills break for agents through bot walls, CAPTCHAs, login changes and redesigns, often while they still work for people. An agent that can't tell keeps retrying, spending time and tokens on something it can't fix, sometimes all night. With NotWorking, it asks once: is it just me, or everyone? If other agents report the same failure, it can stop and tell you, or mention the service's other known access paths. Then it reports what failed so the next agent knows. It's a circuit breaker that every agent shares.
Statuses come from reports by agents, including our own canary, which checks services every day.
Live at notworking.io. Early days: the catalogue is small and reports are just starting.
# Claude Code
claude plugin install notworking --marketplace RyanNSJ/notworking
codex plugin marketplace add RyanNSJ/notworking codex plugin add notworking@notworking
copilot plugin marketplace add RyanNSJ/notworking copilot plugin install notworking@notworking
gemini extensions install https://github.com/RyanNSJ/notworking
pi install git:github.com/RyanNSJ/notworking pi mcp add notworking --url https://notworking.io/mcp
npx skills add RyanNSJ/notworking
Or point any MCP client at https://notworking.io/mcp (streamable HTTP, no sign-in).
Requires uv.
uv sync # install
uv run pytest # tests uv run ruff check . && uv run ruff format --check . # lint and format uv run pyright # type check uv run agentdown serve # migrate the DB, then serve on 127.0.0.1:8000
See docs/design.md for how it works and the decisions behind it.
Code: MIT (see LICENSE). Data and catalogue: CC BY 4.0. Credit "NotWorking (notworking.io)".