Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Web standards and time reference for agents: HTTP codes, retries, deadlines. Paid via x402.
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://webref.johnaio281.workers.dev/mcpRun this in your terminal
claude mcp add --transport http webref https://webref.johnaio281.workers.dev/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"webref": {
"url": "https://webref.johnaio281.workers.dev/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": {
"webref": {
"type": "http",
"url": "https://webref.johnaio281.workers.dev/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://webref.johnaio281.workers.dev/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.
Tool names and descriptions exactly as the server reported them on Nov 7, 2026. The maker wrote them, not us; we show them as plain text.
http_statusLook up an HTTP status code: what it means, what the client must do, whether it is retryable, whether it is safe to replay, the defining RFC and the common causes. ($0.003 per call)
status_for_situationFind the HTTP status code that matches a described situation, when the code is not known in advance — for example 'the caller is being rate limited' or 'upstream returned garbage'. ($0.005 per call)
retry_adviceDecide how a client should react to a status code: retry with backoff, check the outcome before retrying, or do not retry. Includes a suggested backoff schedule. ($0.005 per call)
mime_typeLook up a MIME type by full type or by file extension: the top-level type, what it is for, and the usual file extension. ($0.003 per call)
list_mime_typesList or search MIME types by top-level type or by keyword, for example image types or anything to do with calendars. ($0.003 per call)
content_type_adviceCheck whether a Content-Type header matches what an endpoint kind expects, and say what to send instead when it does not. ($0.003 per call)
http_methodDescribe an HTTP method: whether it is safe, whether it is idempotent, whether it carries a body, and what it is for. ($0.003 per call)
time_untilHow much time is between two instants: the direction, the total in every unit, and a day/hour/minute/second breakdown. Use it to compute a retry delay, a rate-limit reset, or whether a deadline has passed. ($0.003 per call)
describe_instantDescribe an instant: its date, weekday and time in UTC and in Tehran local time (UTC+03:30), plus the Unix timestamp. Use it when a response carries a timestamp and the local date matters. ($0.003 per call)
weekday_ofWhich day of the week a date falls on, and whether it is a business day. Use it before scheduling work or setting a deadline that lands on a weekend. ($0.003 per call)
business_days_betweenCount the business days between two dates, excluding weekends. Use it to turn a calendar deadline into a working-day deadline. Public holidays are not excluded, so the count is an upper bound. ($0.005 per call)
add_durationAdd a duration to an instant and get the result, in UTC and in Tehran local time. Use it for a TTL, a lock expiry, or a token lifetime. ($0.003 per call)
convert_durationConvert a duration between units and get it in plain language. Use it to express a timeout in the unit the caller asked for, or to check whether a limit is seconds, minutes or milliseconds. ($0.003 per call)
unix_timeConvert between a date and a Unix timestamp, in either direction. Use it when a payload carries one and the other is needed. ($0.003 per call)
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 against the domain webref.johnaio281.workers.dev (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 983 ms (HTTP 200)
No sign-in needed
Read 14 tool descriptions and found no hidden instructions to the AI
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 (1.8.0) reached the registry 9 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, 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.
No README found in the repo