Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Exact utilities for agents: time zones, date math, business days, calculator, units, validation.
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.
AuthorizationValues 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 …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http plumbkit https://plumbkit.dev/mcp --header 'Authorization: your-value'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"plumbkit": {
"url": "https://plumbkit.dev/mcp",
"headers": {
"Authorization": "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": {
"plumbkit": {
"type": "http",
"url": "https://plumbkit.dev/mcp",
"headers": {
"Authorization": "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 address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
Authorization secret HTTP headerThese 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 8, 2026. The maker wrote them, not us; we show them as plain text.
current_timeReturns the exact current date, time, weekday and UTC offset in any time zone. Use this whenever you need to know today's date or the current time instead of guessing — your training data does not know what day it is.
convert_timezoneConverts a date/time from one time zone to another, correctly handling daylight saving time. If the input already includes an offset or 'Z', from_timezone is ignored.
date_addAdds or subtracts a duration (years, months, weeks, days, hours, minutes, seconds) to a date/time. Use negative numbers to subtract. Calendar-aware: adding 1 month to Jan 31 gives Feb 28/29, and adding days keeps the same local clock time across daylight-saving changes.
date_diffCalculates the exact time between two dates/times: a calendar breakdown (years, months, days, hours, minutes, seconds) plus totals in days, hours, minutes and seconds, and the number of calendar days. Negative if end is before start.
business_daysWorks with business (working) days. mode "add": returns the date N business days after start_date (start_date itself is not counted; negative N goes backward; 0 returns start_date, or the next business day if start_date is not one). mode "count": counts business days from start_d
calculateEvaluates an arithmetic expression exactly, so you don't have to do mental math. Supports + - * / % ^ (or **), parentheses, constants pi/e/tau and functions: sqrt, cbrt, abs, round(x, digits), floor, ceil, trunc, sign, ln, log(x[, base]), log10, log2, exp, pow, sin, cos, tan, asi
convert_unitsConverts a value between units of length, mass, volume (US and imperial), area, speed, time, digital data (KB vs KiB, bits vs bytes), energy, pressure and temperature. Accepts common abbreviations (km, lb, fl oz, mph, °F, GiB). US customary units are used for cup/pint/quart/gallo
text_statsCounts exactly what language models are bad at counting: characters (as humans see them), words, lines, sentences, paragraphs, UTF-8 bytes, and occurrences of a letter or substring (e.g. how many "r" in "strawberry"). Use it to check length limits (tweets, SMS, meta descriptions,
hash_textComputes a cryptographic hash (SHA-1, SHA-256, SHA-384, SHA-512) of text, or encodes/decodes it as Base64, Base64URL, hex or URL-encoding. Text is treated as UTF-8.
regex_testRuns a JavaScript regular expression against text and returns every match with its position and capture groups, or the text after replacement. Use it to verify a regex actually works before relying on it.
validate_emailChecks whether an email address is correctly formatted and returns a normalized version. Set check_dns=true to also confirm the domain exists and can receive mail (MX records). Does not send email and cannot confirm that a specific mailbox exists.
validate_phoneValidates a phone number using Google's libphonenumber rules and returns it in E.164 (+14155552671), international and national formats, plus the country and line type (mobile, fixed line, toll free...). For numbers without a +country code, pass default_country.
validate_urlChecks that a URL is well-formed, normalizes it (lowercase host, punycode, default ports removed, spaces encoded) and splits it into parts including each query parameter. Flags common problems such as missing scheme, private/localhost addresses and credentials embedded in the URL
validate_ibanValidates an International Bank Account Number: country, length for that country, and the mod-97 check digits. Returns electronic and printed formats. A valid IBAN is correctly formed; this does not confirm the account exists.
json_repairTurns almost-JSON into valid JSON: removes markdown code fences, comments and trailing commas, adds missing quotes, commas and closing brackets, converts single quotes, Python True/False/None and truncated output. Returns the repaired JSON string and whether the input was already
json_schema_validateChecks a JSON value against a JSON Schema (drafts 4, 7, 2019-09 and 2020-12) and lists every violation with its location. Use it to confirm structured output or an API payload is correct before sending it. `data` and `schema` may be JSON values or JSON strings.
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 8, 2026
The registry lists no source repo, so we cannot match the publisher (plumbkit.dev) to the code
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 119 ms (HTTP 200)
No sign-in needed
Read 16 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 2 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.
You need to fill in: Authorization
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 (1.0.0) reached the registry 24 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, Tethered Trust
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.
Fit, compatibility and recall checks for AI agents before they buy: verdicts, evidence, receipts.
No README found in the repo