AI/Search with AI

AI/Search with AI Guide

Log in Share appShare

Tsukutta

Log in Guide Free Browser Games Stats & data Idea Board For developers What's new Contact Us Survey Terms of Service Privacy Policy Commercial transactions disclosure

© 2026 Tsukutta.

Non-English Normalizer-MCP-Server - Data Processing | Tsukutta

Top > Data Processing > Non-English Normalizer-MCP-Server

Non-English Normalizer-MCP-Server - Screenshot 1

Non-English Normalizer-MCP-Server - Screenshot 1

Non-English Normalizer-MCP-Server

This is an MCP extension for Gemini CLI that completely prevents character corruption (Shift-JIS, etc.) in Windows environments and enables AI to accurately analyze code and documents from non-English-speaking regions.

Data Processing

About this appAbout this app

Automatically translated from Japanese by AI

Reactions & commentsFeedback

Share your thoughts, bug reports, or suggestions directly with the developer

Log in to share your feedback

Log in to leave feedback

Up nextDiscover more apps

SUGUDASU 全角半角整え

#全角半角整え #Excel列

SUGUDASU 全角半角整え

Excel列の全角半角や空白を社内規程NGでもその場で整え

多機能画像編集

#画像編集 #リサイズ

多機能画像編集

Zero Data Leakage Browser-Based Image Editing Features 🔹Image Scaling 🔹Batch Resize & ZIP Output 🔹Color Correction 🔹Metadata Removal, Text Insertion

MojiGacha (Random String Generation)

#ランダム文字列生成 #CLI

MojiGacha (Random String Generation)

CLI compatible! Random string creation app

character rearrangement nPn

#順列生成 #文字列ツール

character rearrangement nPn

This is an app that rearranges all input characters for every combination. The preview shows the first 500 items, but you can load more. You can output as .txt or .md files. (I created this because I'm not good at riddles where you rearrange characters)

Yuzuko Underson26♥ 1

ｲﾝﾑ語変換器

#言葉遊び #ネタ翻訳

ｲﾝﾑ語変換器

This is bad!! ※This is filthy garbage with a stinky modification added to the "Pump Language Translator" that was posted on a certain programming site. In short, it's a project made in Sc○atch, so it's seriously half-baked. Of course, I have neither the motivation nor the time to rewrite it in JS. Since AI was used to collect the vocabulary, there might be some quotes that don't actually exist?

nyantorusabu120

簡単シンプル画像イメージ変換コンバーター

#画像変換 #形式変換

簡単シンプル画像イメージ変換コンバーター

It's a common image conversion site. I've also added a simple drawing/doodling feature like a snipping tool. It can read HEIC, .psd, and .ai files as well.

Yuzuko Underson44

Suidasu - Extract data from images

#OCR #データ抽出

Suidasu - Extract data from images

Suidasu is a cloud service that leverages AI to automatically extract necessary data from images and PDFs. It supports improvements in system input operations across various industries.

Miyatake Masaya147

AI診査に強い【転職用】履歴書作成ツール

#転職 #履歴書

AI診査に強い【転職用】履歴書作成ツール

A resume creation tool specialized for career transitions of foreigners and designers. Developed and used together with a Bangladesh coder and a designer in career transition.

Designart Evita10

MJUN

#Markdown #ブログ

MJUN

You can write a blog without writing HTML, using Markdown!

Yuzuko Underson20

多機能PDF編集

多機能PDF編集

Zero Data Leakage Browser-Based PDF Editing Features 🔹Convert PDF to Excel/CSV/Images 🔹Merge Multiple Files & Split Specified Ranges 🔹Intuitive Handwritten Signature Embedding 🔹Page Rotation

abmc-ollama

#ローカルLLM #CLI

abmc-ollama

abmc-ollama https://github.com/DovahkiinYuzuko/abmc-ollama When opening a local LLM model from the command prompt, the repetitive input from to was tedious, so I created this CLI app with the motto of "a bit more convenient." I've made installer(OS).py for Windows, Mac, and Linux respectively, so startup should be straightforward. You can launch it with ■ What This Tool Can Do [1] Run / Chat: Standard interactive mode. [2] Add Model (Pull): Download a new model by entering its name. [3] Remove Model (Remove): Delete unnecessary models from the list. [4] Check Status (Status): Monitor operational status on VRAM. [5] AI Search Chat: Automatic search mode using multi-stage RAG chains. As you can see, since command input was tedious, I made it possible to select models by number. The AI search chat is a bonus feature—I've designed it so that even weaker models can find relevant information by having one model handle multiple roles. ■ Role Division [1] Planner (Planning): Analyzes the user's question and creates up to 5 optimal search queries for resolution. [2] Searcher (Collection): Uses the queries created by the Planner to actually search the web (Brave, DuckDuckGo, etc.). (You can choose your own search engine if you input an API) [3] Extractor (Extraction/Verification): Extracts only "facts" related to the question from the large amount of collected data. Discards outdated information by date, verifies that numerical units are correct, and carefully selects the "materials" for the answer. [4] Writer (Writing): Based only on the "facts" selected by the Extractor, writes the final answer. Acts as an anchor to suppress AI's arbitrary assumptions (hallucinations) and produce accurate, evidence-based responses. (Not all can be prevented.) It's not a particularly useful tool. The search function is essentially just a bonus feature. However, if Tools can be used, even a 4B model will (regardless of accuracy) investigate and compile information. Instead of breaking the session each time, I use JSON to bridge information between stages.

Yuzuko Underson56

note XML to Markdown conversion -MyRuleMarkdown-

#note変換 #XML→MD

note XML to Markdown conversion -MyRuleMarkdown-

For note writers. This is the .xml file that appears when you use the note article export feature. Some LLMs had trouble reading it, which was a hassle, so I made it possible to convert it to .md. Now you can easily share information by feeding it to an LLM. I also think you'll be able to do your own analysis if you use it as a source for NotebookLM.

Yuzuko Underson22

Monochrome image partial colorization

#画像編集 #モノクロ加工

Monochrome image partial colorization

Only the parts you trace change color! A "Monochrome Partial Colorization" tool that creates emotional photos in seconds. It comes with automatic skin tone restoration and background removal, so anyone can easily create stylish art!

Simple Markdown, LaTeX editor

#Markdownエディタ #テンプレート

Simple Markdown, LaTeX editor

Markdown, LaTeX and preview side by side at a glance! Even without memorizing difficult code, you can quickly create documents with intuitive buttons and convenient templates.

mdhenkan

#markdown #html

mdhenkan

Convert Markdown to HTML, PDF, Word. Free browser conversion tool with no registration required.

Penguin Control Center (PCC) — Manage Linux CLI through GUI while learning

Penguin Control Center (PCC) — Manage Linux CLI through GUI while learning

Every time you operate via GUI, the CLI commands being executed behind the scenes are visible as-is. A GUI version of a Linux management tool × learning tool.

Managing Libraries is a Drag

#ライブラリ管理 #Python

Managing Libraries is a Drag

A library warehouse where you can casually store the libraries you're using. We'll compile what libraries were being used in lib-WH.

Yuzuko Underson24

DraftPad — A draft notepad for calmly writing sentences to send to AI before pasting them

#下書き #テキスト入力

DraftPad — A draft notepad for calmly writing sentences to send to AI before pasting them

Draft notepad for chat column. Paste to the other person's input field with one button. Convenient when multiple input fields get tangled up.

石ちゃんNEW28

DDO Saba

#Ollama #LLM推論サーバー

DDO Saba

誰でもオンラインOllamaサーバーをホストできるパッケージ

Yuzuko Underson22

SkinGetBE | Minecraft Bedrock Edition Skin Acquisition Tool

#skin #minecraft

SkinGetBE | Minecraft Bedrock Edition Skin Acquisition Tool

Free tool to retrieve and save Minecraft Bedrock Edition player skins.

TextEditImage

TextEditImage

Edit Text in Image Free — AI Photo Text Editor Online

【新CoC用】現代探索者信用収入簡易入力

#クトゥルフ神話TRPG #キャラクター作成

【新CoC用】現代探索者信用収入簡易入力

This is a tool for the new Call of Cthulhu TRPG that automatically calculates annual income and assets based on your Credit skill value. It also formats the output so you can easily copy and paste it directly into your character sheet. It includes over 10 different world currencies, so it's useful for creating investigators with a worldwide setting. ※Since it references the current exchange rates at the time, the numerical values will change considerably. The basic rulebook outputs values in dollars based on the Credit skill value. This app also simply converts the dollar values using exchange rates, so if you wanted to match the dollar values from around 2017, please calculate accordingly using the exchange rates from that time.

Yuzuko Underson36

ポジティブジェネレーター

#悩み相談 #ポジティブ変換

ポジティブジェネレーター

悩みを入力するとポジティブに返してくれます。

どこかの30歳51

Easy PDF [No Upload Required] Add Signatures and Stamp Images to PDF

Easy PDF [No Upload Required] Add Signatures and Stamp Images to PDF

No upload required. A one-time purchase Windows software that simply pastes text and stamp images onto PDFs and saves them.

2

·37

3702

Log in to react, save and follow.

Made by

Details

PublishedApr 28, 2026

UpdatedSep 21, 2026

CategoryData Processing

Uses2

Discover more apps by swipingKeep discovering by swipe →

Data Processing

#文字コード変換

#MCP拡張機能

#コード解析

I created an MCP server to "roughly convert various character codes to UTF-8 for normalization" because Japanese characters get severely garbled when reading files on PowerShell. It's designed for Gemini CLI, but I think it can also be used with other CLI agent tools.

Additionally, it has partial language support for structural analysis using Tree-sitter, which improves the efficiency of AI understanding code.

Advanced reading: You can read not just the entire file, but also the end or specified ranges, allowing pinpoint reading.

Binary support: If the character code is unknown, you can check the contents in hexdump format.

Windows path issues: Windows-specific path errors are already avoided.

What it does is mundane, but I think there are many scenarios where it's useful. Non-Japanese local character codes that are supported can also be normalized.

Yuzuko Underson

57 published · 348 uses

Report a problem