MCP File Tools

Claude sees Настройки — not ???? or Íàñòðîéêè.

MCP server for file operations on text that isn't UTF-8. It detects the encoding from the file's bytes rather than its extension, hands the model UTF-8, and writes back in the original encoding — BOM and CRLF/LF intact, still byte-compatible with whatever legacy tool owns the file.

• 25 encodings, read and write — Cyrillic (CP1251, KOI8-R/U, CP866), Windows-125x, ISO-8859-x, UTF-16 LE/BE, GBK/GB18030 (full list)
• Encoding-aware across the whole tool set — not just read and write: edit_file, grep_text_files and search_files decode the same way
• Detection you can inspect — detect_encoding reports the charset, a confidence score and any BOM, so garbled text becomes diagnosable instead of mysterious
• BOM and line endings are first-class — add or strip a BOM, convert CRLF↔LF, and do it correctly on UTF-16, where a naive byte-level rewrite corrupts the file
• Sandboxed — every path, including symlink and junction targets, is resolved and checked against the directories you allowed

Built for: Delphi/Pascal units with Cyrillic UI text (Windows-1251), VB6 forms (Windows-1252), legacy PHP/HTML with localized content (CP1251, ISO-8859-1), and INI or data files whose encoding you can't tell from the filename.

User: Read config.ini and change the title to "Настройки"
Claude: [read_text_file → cp1251 detected] → [edits UTF-8] → [write_file → back to cp1251]

PRs welcome and merged fast — no CLA, no style review, one-line fixes count. Forked this to fix something? Please send it back instead.

Tools

20 tools — every one that touches text content is encoding-aware:

• read_text_file - Read files with encoding auto-detection and conversion
• read_multiple_files - Read multiple files concurrently with encoding support
• write_file - Write files in specific encodings
• edit_file - Line-based edits with diff preview and whitespace-flexible matching
• copy_file - Copy a file to a new location
• delete_file - Delete a file
• list_directory - Browse directories with pattern filtering
• tree - Compact indented tree view, optionally annotated with each file's encoding
• search_files - Recursively search for files matching glob patterns
• grep_text_files - Regex search in file contents with encoding support
• detect_encoding - Auto-detect file encoding with confidence score
• convert_encoding - Convert file between encodings
• manage_line_endings - Detect or convert line endings (CRLF/LF/

... View full README on GitHub