cofferdock

Give your AI assistant 25 tools that create real files: HTML to image and PDF, website screenshots, QR codes, charts, PDF editing, image conversion, zips and…

От сообществаРаботаетНужен API-ключГлобальныйБесплатноМожет изменять данные

Что умеет

  • Get Status: Check your plan and remaining credits. Returns your plan, the monthly limit, how many credits you have used and how many are left. Free: does not cost a credit. Useful at the start of a wo
  • Html To Image: HTML to image (PNG, JPEG or WebP). Renders HTML (with inline CSS; fonts and images from the internet are allowed, JavaScript is not executed) into an image. Ideal for social cards, cert
  • Html To Pdf: HTML to PDF. Renders HTML into a PDF (invoices, reports, tickets, contracts). Same rendering engine as /capture: inline CSS, web fonts and images allowed, no JavaScript. Send either html,

Какие данные видит

Нужен ли аккаунт

Нужен API-ключ из настроек сервиса

Give your AI assistant 25 tools that create real files: HTML to image and PDF, website screenshots, QR codes, charts, PDF editing, image conversion, zips and validators.

Как подключить

Как подключить cofferdock к Claude

Адрес сервера, который нужно вставить в настройках Claude:

https://cofferdock--contacto-y9sc.run.tools

  1. Откройте Claude (сайт claude.ai или приложение для компьютера).
  2. Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
  3. Нажмите Добавить пользовательский коннектор (Add custom connector).
  4. Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
  5. В чате нажмите + → Коннекторы и включите новый коннектор.

Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.

Авторизация

После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.

Как подключить cofferdock к ChatGPT

Адрес сервера, который нужно вставить в настройках ChatGPT:

https://cofferdock--contacto-y9sc.run.tools

  1. Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
  2. Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
  3. Откройте Настройки → Коннекторы и нажмите Создать (Create).
  4. Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
  5. В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
  6. В новом чате откройте + → Приложения/Коннекторы и включите коннектор.

Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.

Авторизация

При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.

Как подключить cofferdock к Cursor

Адрес сервера, который нужно вставить в настройках Cursor:

https://cofferdock--contacto-y9sc.run.tools

Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.

Вручную:

  1. В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
  2. Вставьте JSON, скопированный ниже, в открывшийся файл ~/.cursor/mcp.json (для одного проекта: .cursor/mcp.json в корне проекта).
  3. Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.

Авторизация

Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.

Список инструментов сервера (26)

Технические названия из tools/list. Нужны только разработчикам.

get_statusCheck your plan and remaining credits. Returns your plan, the monthly limit, how many credits you have used and how many are left. Free: does not cost a credit. Useful at the start of a workflow to decide whether to continue.
html_to_imageHTML to image (PNG, JPEG or WebP). Renders HTML (with inline CSS; fonts and images from the internet are allowed, JavaScript is not executed) into an image. Ideal for social cards, certificates, tickets, OG images or any design you can describe in HTML. Send either html, or template + data to use a ready-made design. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
html_to_pdfHTML to PDF. Renders HTML into a PDF (invoices, reports, tickets, contracts). Same rendering engine as /capture: inline CSS, web fonts and images allowed, no JavaScript. Send either html, or template + data (the "invoice" template works well as a PDF). Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
screenshot_urlScreenshot of a public web page. Loads a public URL in a real browser (JavaScript enabled) and takes a screenshot. Private networks and internal addresses are blocked. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
generate_qrQR code (PNG or SVG). Turns a link or any text (max 1500 characters) into a QR code. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
data_to_chartData to chart image (bar, line, pie, doughnut, radar). Turns labels and numeric series into a chart image, without a browser. Pie and doughnut accept 1 series only. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
transform_imageResize, convert or compress an image. Resizes (with a fit mode), converts between JPEG/PNG/WebP/AVIF and/or compresses ONE image. Provide at least one of width, height, format or quality. Input formats: PNG, JPEG, WebP, AVIF, GIF, TIFF. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
merge_pdfsMerge 2 to 20 PDFs into one. Joins several PDFs in the order given. One credit regardless of how many files. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
split_pdfSplit a PDF by page ranges. Creates one PDF per range. Ranges use 1-indexed pages: "1-3,5,7-9" gives three files. For one file per page, list every page: "1,2,3". One credit regardless of how many files come out. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
rotate_pdfRotate pages of a PDF. Rotates all pages, or only the ones in `pages`, by 90, 180 or 270 degrees (added to the rotation each page already has). Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
watermark_pdfAdd a text or image watermark to a PDF. Overlays a text (max 200 characters) OR a PNG/JPEG image on every page (or on `pages`). Image watermarks need the JSON body. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
fill_pdf_formFill a PDF form (or list its fields). Fills the fields of an existing PDF form (AcroForm) with the values in `data`. Without `data` (or with inspect=true) it returns the list of fields instead, so you know their names. Set flatten=true to make the result non-editable. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
extract_pdf_textExtract the text of a PDF. Returns the text of a PDF (not scanned images: there is no OCR). Set pages=true to also get the text page by page. Costs 1 credit per call.
add_pdf_page_numbersAdd page numbers to a PDF. Stamps a page number on every page (or on `pages`). The `format` text must contain {n}; it can also use {total}. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
pdf_metadataRead or write PDF metadata. With no metadata fields it READS title, author, subject, keywords, creator, producer and dates. With any field given it WRITES them and returns the PDF. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
images_to_pdfImages to PDF (one image per page). Turns 1 to 20 PNG/JPEG images into a PDF. page_size "auto" makes each page the size of its image; A4, A3, A5, Letter, Legal or Tabloid fit the image inside. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
pdf_to_imagesPDF pages to PNG images. Renders each page (or the ones in `pages`) as a PNG. `scale` 1 is 72 dpi; 2 is 144 dpi. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
protect_pdfAdd a password to a PDF. Encrypts the PDF so it asks for the password when opened. The PDF must not be protected already. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
unprotect_pdfRemove the password of a PDF (you must know it). Returns an unencrypted copy of a password-protected PDF. It does not crack passwords: the current one is required. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
create_zipCreate a zip from up to 50 files. Packs files of any type into a .zip. Names can include folders ("reports/january.pdf"). Default output is the zip binary. Costs 1 credit per call. Returns a temporary download link (valid 15 minutes). Always include that link in your reply so the user can open or download the file.
validate_emailValidate an email address. Checks the format and, by default, that the domain has a real mail server (MX record). An invalid email is still a successful call (valid=false). Costs 1 credit per call.
validate_phoneValidate and format a phone number. Validates an international phone number and returns it in E.164 and international formats, with its country and type (mobile, fixed line...). Give `country` (2-letter code) for numbers without the + prefix. Costs 1 credit per call.
validate_ibanValidate an IBAN. Checks the IBAN checksum (ISO 7064) and returns the country and the formatted IBAN. Costs 1 credit per call.
generate_uuidGenerate UUIDs (v4). Returns 1 to 100 random UUIDs. One credit per call regardless of count. Costs 1 credit per call.
slugifyText to URL slug. Lowercases, removes accents and keeps only letters and digits separated by `separator`. "Año Nuevo 2026!" becomes "ano-nuevo-2026". Costs 1 credit per call.
hashHash a text or a file (md5, sha1, sha256, sha512). Returns the hash of a text (JSON) or of a file (raw bytes, max 25 MB). Useful for checksums and deduplication. Costs 1 credit per call.