dimitar-grigorov/mcp-file-tools

Overview

MCP server for file operations on non-UTF-8 text. Detects the encoding from bytes, converts to UTF-8 for the model, and writes back in the original encoding with BOM and CRLF/LF intact. Supports 24 encodings including Cyrillic, Western European, KOI8, ISO-8859, UTF-16, and GBK.

Best for

Best for
Developers working with legacy encoded text files in MCP-based workflows

Use cases

• Reading legacy files with CP1251 or KOI8 encodings
• Editing files without corrupting original encoding and line endings
• Processing GBK or UTF-16 documents through an MCP client

How to use

Install

npx @modelcontextprotocol/inspector go run ./cmd/mcp-file-tools -- /path/to/allowed/dir

Tools exposed

• MCP_DEFAULT_ENCODING
• MCP_DEFAULT_LINE_ENDINGS
• MCP_MEMORY_THRESHOLD
• MCP_DETECTION_CANDIDATES
• MCP_FILE_TOOLS_ALLOWED_DIRS
• MCP_FILE_TOOLS_NO_CWD_FALLBACK

Tested with

Claude Desktop, Claude Code, Cursor, VS Code, ChatGPT

Notes

MCP server for file operations on non-UTF-8 text. Detects the encoding from bytes, converts to UTF-8 for the model, and writes back in the original encoding with BOM and CRLF/LF intact. Supports 24 encodings including Cyrillic, Western European, KOI8, ISO-8859, UTF-16, and GBK.

22 stars on GitHub. Last updated 2026-09-02. Licensed GPL-3.0.

Use cases

• Reading legacy files with CP1251 or KOI8 encodings
• Editing files without corrupting original encoding and line endings
• Processing GBK or UTF-16 documents through an MCP client

Pros

• Preserves original encoding, BOM, and CRLF/LF
• Supports a wide range of legacy encodings
• Simple Go implementation, easy to deploy

Cons

• Limited to file operations, not a general-purpose tool
• Small community (22 stars), may lack extensive testing
• Requires MCP client integration

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.