mcpField
M
MCP File System Server

MCP File System Server

Local
github.com/kvas-itFiles & Storage4Updated 86w ago

About MCP File System Server

MCP File System Server exposes file, directory, search, and analysis operations, along with shell command execution. It is intended for MCP clients that need to work with files and projects on the host.

Key features

  1. 01Browse and manage files and directories
  2. 02Read and write files
  3. 03Search with regular expressions
  4. 04Summarize Python and Markdown files
  5. 05Run ruff checks and formatting
  6. 06Execute shell commands

Use cases

  1. 01Explore a project directory
  2. 02Read, edit, or move project files
  3. 03Find matching text across files
  4. 04Review file structure and run ruff

MCP support

Provides MCP clients with tools for filesystem operations, file analysis, project navigation, code quality checks, and shell execution. Shell commands allow arbitrary host command execution.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP File System Server

MCP server providing file system operations. Supports navigation, reading, writing, analyzing files and command execution.

Tools

File and Directory Operations
  • ls(path) - List directory contents
  • cd(path) - Change working directory (supports home directory expansion with ~)
  • read_file(path) - Read file contents
  • write_file(path, content) - Write content to a file
  • mkdir(path) - Create directory
  • rm(path) - Remove file or empty directory
  • rmdir(path) - Remove directory and contents recursively
  • cp(src, dst) - Copy file or directory
  • mv(src, dst) - Move file or directory
Editing and Searching
  • edit_file(path, changes) - Apply multiple search/replace operations to a file, where changes is a list of (search_text, replace_text) tuples
  • grep(pattern, path) - Search for regex pattern in file(s)
Analysis
  • summary(path) - Generate summary of Python (.py) and Markdown (.md) files:
    • Python: Lists functions and classes
    • Markdown: Lists headers (lines starting with #)
Batch Operations
  • read_files(paths) - Read multiple files, returns dict mapping paths to contents
  • summarize(paths) - Generate summaries for multiple files, returns dict mapping paths to summaries
Project Navigation
  • work_on(path) - Change to directory, list its contents, and get the notes from CLAUDE.md. Useful for getting familiar with a project at the start of a chat
Code Quality
  • ruff_check(paths) - Run ruff linter on specified files
  • ruff_format(paths) - Format files using ruff
Command Execution
  • shell_command(command, args=None, cmdline=None, timeout=30) - Run shell commands and capture their output

    ⚠️ Security Warning: This tool allows arbitrary command execution on the host system. Always inspect and validate commands before allowing them to run, especially if the input source is untrusted.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.