mcp-chunk-editor
If you are the rightful owner of mcp-chunk-editor and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
MCP Chunk Editor is a Model Context Protocol server that provides chunk-oriented text file editing capabilities for LLMs, enabling more natural and efficient editing operations.
MCP Chunk Editor is designed to facilitate chunk-oriented text file editing for Language Model Machines (LLMs). By utilizing semantic chunking, the server allows LLMs to edit files based on meaningful code structures such as functions, classes, and methods, rather than relying on line numbers. This approach enhances the naturalness and efficiency of editing operations. The server supports immediate application of changes with preview generation for verification, simple undo functionality, and is optimized for LLM token usage through incremental updates and lazy chunking. It requires Python 3.10 or 3.11 and Universal CTags for operation.
Features
- Semantic Chunking: Uses Universal CTags to identify meaningful code structures like functions, classes, and methods.
- Immediate Application: Changes are applied immediately with preview generation for verification.
- Simple Undo: Supports reverting the most recent change for each file.
- Efficiency: Optimized for LLM token usage with incremental updates and lazy chunking.
Tools
read_chunks
Retrieve chunks of a file, either all chunks or a specific range.
replace_chunks
Replace the content of one or more chunks and immediately apply the changes.
undo
Revert the last change made by a replace_chunks operation.
create_file
Create a new file with given content.
delete_file
Delete a file.
