Ciro Cesar Maciel — Free Tools MCP Server

Draws a background or wallpaper at the exact size of a place: YouTube banner, Instagram story, LinkedIn cover, desktop up to 4K here (8K on the web page), phones, video calls, slides. WHEN TO USE: the user wants a background, wallpaper, cover or banner image for a channel, profile, screen or presentation, or asks what size one of these must be. HOW IT WORKS: pick `format` (70 places, each with its size and the safe area that every device shows) and `style` (blurred petals, veils and hills; steps; geometry such as arcs, tiles, scales, rays; Hilbert curve; folds). `colors` are 3 to 7 hex colors, first one is the background. The same `seed` draws the same design in every format, so a set matches. RETURNS: width, height, format (name, ratio, safe_area in pixels of the file), files (png, jpg and webp addresses: download with curl -o; null above 4K), and link (the web page with the same options, to adjust, add a screenshot on top or download up to 8K).

Generates a complete favicon set from 1 to 3 characters (initials) or one emoji. WHEN TO USE: the user needs a favicon, tab icon, apple-touch-icon or web app icon for a website or web app, or the project still has a framework's default icon. PRIORITY: if the host also provides open_favicon_editor, call that editor first for every normal favicon request (create, preview, adjust or download). Use this data tool directly only when the user explicitly asks for files, SVG, head tags or installation text to write into a code project. HOW IT WORKS: mode text draws the characters in any Google Font as vector paths (no font dependency); mode emoji draws one Twemoji emoji as vectors, with a margin. Both sit inside a shape. With adaptive=true the SVG swaps its colors when the browser is in dark mode. Pass framework to get where each file goes. For a logo or other picture, use open_favicon_editor with mode=image when available: the user chooses the image in its private file picker. Otherwise return the link with mode=image; do not process a chat attachment as an image favicon here. RETURNS: svg (write it to disk exactly as given), files (each with path and url: download the binaries with curl -o), manifest (path and content), html (the head tags; null on Next.js App Router), inline (the whole favicon as one <link> tag, no files), install (steps for the framework), warnings, credit (emoji only), and link (this tool's web page with the same options, to adjust and preview).

Generates a strong random password with a cryptographically secure generator. WHEN TO USE: the user asks for a password or a random key. HOW IT WORKS: always uses upper and lower case letters; numbers and symbols are optional. Each selected kind of character appears at least once. length: 8 to 64 (default 16). RETURNS: password, the options used, and link — this tool's web page with the same options. The password is never in the link. Show the password to the user as it is; do not store it or repeat it elsewhere.

Converts one moment across several time zones, daylight saving time included. WHEN TO USE: "what time is it in…", scheduling a meeting across cities, checking whether a time falls at night or on another day somewhere. HOW IT WORKS: - zones: IANA time zone names in Area/City form — America/Sao_Paulo, Europe/Lisbon, Asia/Tokyo, UTC. Not city names alone, abbreviations (EST, BRT) or offsets (GMT-3). The FIRST zone is the reference for date and hour. 1 to 12 zones. - date (YYYY-MM-DD) and hour (0–23) are read in the first zone. Without them: the current moment. Only hour: that hour today in the first zone. Only date: that day at the current hour. - format: 24h (14:00) or 12h (2:00 PM). RETURNS: the moment in UTC and, for each zone, its local date, weekday, time, UTC offset and dayShift (+1 = next day, -1 = previous day, relative to the first zone). link: this tool's web page with the same comparison. ERRORS name the unknown zone or the invalid date; fix it and call again.

Draws a chart from a CSV table and returns it as an image. WHEN TO USE: the user wants to see data as a chart, or needs a chart image for a document, a README, a slide or a chat. HOW IT WORKS: - csv: a header row, then data rows. First column: the category (or x value); the next columns: numbers. Use a comma or semicolon as separator; decimals with a point, or with a comma when the separator is a semicolon. Up to 20,000 characters. - chartType, and what each one needs: bar, horizontalBar, line, area, pie, donut, funnel — one category column + one numeric column; multiline — one x column + one or more numeric columns (one line per column); scatter — two numeric columns (x, y); heatmap — three columns: row, column, value. - title: optional, drawn at the top. RETURNS: - image: a PNG address that IS the chart (rendered on request) — put it straight into Markdown () or an <img>. imageSvg: the same as SVG, sharper where SVG is accepted. Both are null when the CSV is too long to fit in an address; then use svg. - svg: the chart as SVG markup. - link: this tool's web page with the same chart, to edit it. ERRORS say what is wrong with the CSV (missing columns, non-numeric values, too many rows); fix the data and call again.

Create and edit mind maps from an outline or a project file. Export PNG, SVG and PDF, save locally and share a link. No account required.

Reads a text aloud with a Microsoft neural voice (the voices of Edge's "Read aloud") and returns an MP3. WHEN TO USE: the user wants to hear a text or needs an audio file of it — narration, audiobook, lesson, voice-over, a message read aloud. HOW IT WORKS: - Up to 50,000 characters per call. A text over 1,000 characters is split by sentence into parts of up to 1,000; each part is voiced in order and the parts are joined into ONE MP3. Progress is reported per part ("Gerando áudio... 3 de 18"), so keep waiting while it arrives. - It takes time: about 5 seconds per part. 5,000 characters ≈ 30 s; 16,000 ≈ 2 min; 50,000 ≈ 6 min. - Over 50,000 characters: split the text at paragraph boundaries into several calls with the same voice and speed, and give the user every link, in order. - Send the text as it should be HEARD: remove Markdown marks (**, #, list bullets), URLs, emojis and tables. Do not summarize, translate or reword unless the user asked — every word you send is read. - voice: choose one in the language of the text (the prefix is language-region: pt-BR, pt-PT, en-US, es-MX…). Brazilian Portuguese: pt-BR-FranciscaNeural (female, default) or pt-BR-AntonioNeural (male). - speed: 1 is the voice's natural pace; 0.9 suits calm narration, 1.2 a quick read. RETURNS: - audioUrl: the complete MP3 to download, valid for 7 days. Always give this link to the user. If you can run commands, you can download it (e.g. curl -o audio.mp3 <audioUrl>). - audio: the MP3 itself, only when it is short (about 1.5 minutes or less); otherwise null. - seconds (duration), parts, characters, voice, speed. - link: this tool's web page with the same voice and speed (the text is not in it). ERRORS say what happened and what to do next. If a part fails, no audio is produced and a new call starts again from part 1.

Fetches a public web page and returns its content as clean Markdown. WHEN TO USE: you need to read a page — documentation, an article, a product page — to answer, summarize or quote it; or the user wants a page as Markdown. HOW IT WORKS: - url: a public http(s) address. Private networks, localhost and addresses with credentials are refused. - Reads the HTML the server sends (like a simple browser, without running JavaScript). Pages that build their content with JavaScript have no text to convert — the error says so. - onlyMainContent (default true) drops menus, headers, footers, sidebars, cookie banners and ads. Set false to keep the whole page. - pages above 1 also follows links on the same site (same folder and below), breadth-first, up to that many pages (max 20), respecting robots.txt. Slower: a few seconds per page. - Limits per page: 15 seconds and 5 MB. PDFs and non-HTML files are not converted. RETURNS: for each page, its Markdown with absolute links and images, plus title, description and language when the page has them; pages that failed are listed with the reason. link: this tool's web page with the same request. ERRORS say why the page could not be read and whether retrying makes sense.