Plumbkit MCP server

• Registry namedev.plumbkit/plumbkitverified in the MCP registry

The registry name sits under plumbkit.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-27
• Tools16
• Server calls itselfplumbkit
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 13 ms.

• Its tools do every use case we checked: convert a timestamp between time zones with daylight saving handled; count characters, words and UTF-8 bytes in text; check email, phone and IBAN formats before saving.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP score98 of 100answers 100 · does the job 100 · definitions 93 · context 98 · connects 100
• What an agent can do with it3 of 3 use cases
• Answered100% of days8 of 8 daily checks
• Median first answer111 ms
• Space in an agent's context≈ 3,249 tokensthe definitions of all its tools (16), which an agent carries on every turn
• Tool definitionsA · 93 of 100
• Typed results0 of 16 toolsdeclared outputSchema: results come typed, read once

• Parameters without a type: in 1 of 16
• Parameters without a description: in 6 of 16

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• current_time

  Returns 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_timezone

  Converts 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_add

  Adds 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…

• date_diff

  Calculates 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_days

  Works 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…

• calculate

  Evaluates 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])…

• convert_units

  Converts 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…

• text_stats

  Counts 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…

• hash_text

  Computes 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_test

  Runs 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_email

  Checks 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…

• validate_phone

  Validates 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…

• validate_url

  Checks 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…

• validate_iban

  Validates 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_repair

  Turns 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_schema_validate

  Checks 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…