fast_batch_file_operations
Performs batch operations on multiple files
LABSCO SUMMARY
The file that was too large to read stops being a dead end.
Chunking is the default rather than a flag you remember to set, so a long file, a deep directory and a wide search all come back in pieces you can keep pulling. The edit side is built the same way round: preview_only, expected_replacements and per-edit backups mean a replacement that would hit the wrong text can be seen before it lands.
What it is
A filesystem server built around chunking: 25 tools for reading, writing, searching, editing, moving, compressing and syncing, where large results resume from a continuation token rather than arriving at once.
What you get
- Reads that auto-chunk, accept a line range or byte offset, and resume with a continuation_token — including several files in one call
- Writes with an append mode and directory creation, plus a large-file path that adds streaming, retry, backup and write verification
- Search by filename or file content, and a ripgrep-style code search returning line numbers and context lines
- Exact block edits guarded by expected_replacements and preview_only, a risk-checking variant with a safety level, and multi-block edits applied in one pass
- Directory work: paginated listings with sorting and patterns, a tree to a chosen max_depth, disk usage, and large files found by min_size
- File operations with a safety net — copy, move, delete with backup_before_delete, and batch operations with dry_run
- Archives and synchronisation: compress with exclude patterns and a compression level, extract, and sync two directories with dry_run
Requirements
npx on your PATH, and paths inside the directories the server allows — fast_list_allowed_directories returns that set. No account, no key.
Setup effort
One command — npx -y fast-filesystem-mcp
USE CASES
01
Reading a file too large to return in one response
The read chunks automatically and hands back a continuation token to resume from, and a line range or offset narrows it further when you already know roughly where to look. Several files can be walked in one call.
02
Searching a codebase for where something is used
Content search returns matches with line numbers and surrounding context rather than filenames alone, so the answer is readable without a follow-up read for each hit. Both searches chunk when the result set is large.
03
Applying an exact edit without clobbering the file
The block edit replaces an exact match and can be told how many replacements to expect, so a string that appears more often than you thought fails instead of silently rewriting the file. preview_only shows the change first, and a backup can be written alongside it.
04
Working out what is filling the disk
Disk usage for a path, then the files above a size threshold, then the tree if you still need to see the shape of it — enough to answer the question without a shell.
05
Moving a project directory somewhere else
Sync two directories with a dry run first so the delete list is visible before it happens, or archive the directory with exclude patterns and extract it at the other end.
25 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
fast_compress_files
Compresses files or directories
fast_copy_file
Copies a file or directory
fast_create_directory
Creates a directory
fast_delete_file
Deletes a file or directory
fast_edit_block
Precise block editing: safely replace exact matches (desktop-commander style)
fast_edit_blocks
Processes multiple precise block edits at once (array of fast_edit_block)
fast_edit_multiple_blocks
Edits multiple parts of a file at once
fast_extract_archive
Extracts an archive file
fast_extract_lines
Extracts specific lines from a file
fast_find_large_files
Finds large files
fast_get_directory_tree
Gets the directory tree structure
fast_get_disk_usage
Gets disk usage information
fast_get_file_info
Gets detailed information about a file or directory
fast_large_write_file
Reliably writes large files (with streaming, retry, backup, and verification features)
fast_list_allowed_directories
Lists the allowed directories
fast_list_directory
Lists the contents of a directory (with auto-chunking and pagination support)
fast_move_file
Moves or renames a file or directory
fast_read_file
Reads a file (with auto-chunking support)
fast_read_multiple_files
Reads the content of multiple files simultaneously (supports sequential reading)
fast_safe_edit
Safe smart editing: Detects risks and provides interactive confirmation
fast_search_code
Searches for code (ripgrep-style) - provides auto-chunking, line numbers, and context
fast_search_files
Searches for files (by name/content) - supports auto-chunking, regex, context, and line numbers
fast_sync_directories
Synchronizes two directories
fast_write_file
Writes or modifies a file (provides emoji guidelines)
BEFORE YOU INSTALL
What to know first
Tools you get
25 tools when we connected.
Requires
npx on PATH
CONTEXT COST
Moderate Standing cost
Rated by the size of the 25 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Add the block to your client, or run the command directly.
Server setup
Configuration file
JSON
{
"mcpServers": {
"fast-filesystem-mcp": {
"command": "npx",
"args": [
"-y",
"fast-filesystem-mcp"
]
}
}
}npx
TERMINAL
npx -y fast-filesystem-mcp
