@ConvergentMethods
基本情報
Compile semantic document edits into correct Google Docs batchUpdate requests. UTF-16 arithmetic, cascading index shifts, OT-compatible ordering. MIT licensed.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"arezzo": {
"command": "uvx",
"args": [
"arezzo"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
Arezzo is an MCP server that compiles semantic editing operations into correct Google Docs API batchUpdate request sequences — deterministically. It solves the problem of manual UTF-16 offset calculation for AI agents editing documents, handling complex Unicode like emoji and CJK characters.
Install with pip install arezzo, then run arezzo init to walk through Google OAuth setup and write platform config files. Use the three MCP tools: read_document, edit_document, and validate_operations.
validate_operations.AI agents editing Google Docs via the `batchUpdate` API must calculate UTF-16 code unit offsets for every mutation. A single miscalculation silently corrupts the document. Arezzo compiles semantic operations into correct request sequences deterministically, eliminating offset errors.
Three MCP tools: `read_document` (structural map of the document), `edit_document` (compile and execute up to 23 operation types), and `validate_operations` (dry-run compilation to inspect exact API calls before execution).
Install with `pip install arezzo` and then run `arezzo init` to walk through Google OAuth setup. No other configuration is required beyond OAuth.
Yes. Arezzo performs proper UTF-16 surrogate pair handling for emoji, CJK supplementary characters, and all non-BMP Unicode.
Arezzo uses two-phase compilation: content mutations (insert, delete, replace) are processed in reverse index order first, then format mutations are applied. This produces OT-compatible request sequencing.
Project context your AI can query through MCP — with source evidence.
Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au
Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.
コメント