
Filesystem MCP Server for WSL
Node.js server implementing Model Context Protocol that enables seamless interaction between Windows and Linux distributions under WSL, allowing file operations like reading, writing, searching, and managing files across the WSL filesystem from Windows.
README
⚠️ IMPORTANT INFORMATION: The original Filesystem MCP Server can already access WSL files by simply using the network path
\\wsl.localhost\DistributionName
as a parameter in the configuration. Example:
{ "mcpServers": { "filesystem": { "command": "npx", "args": [ "-y", "@modelcontextprotocol/server-filesystem", "\\\\wsl.localhost\\Debian", "/path/to/other/allowed/dir" ] } } }
This project remains available for specific use cases and as an example of alternative implementation, but for most users, using the original MCP server with the native network path is probably simpler.
Filesystem MCP Server for WSL
Node.js server implementing Model Context Protocol (MCP) specifically designed for filesystem operations in Windows Subsystem for Linux (WSL). This project is a fork of the original Filesystem MCP Server but completely reimagined for WSL environments. Unlike the original project which handles generic file operations, this version focuses exclusively on seamless interaction between Windows and Linux distributions under WSL. Both projects are compatible and can run in parallel on the same system.
Features
- Access any WSL distribution from Windows
- Read/write files in WSL from Windows host
- Create/list/delete directories in WSL
- Move files/directories across WSL filesystem
- Search files within WSL
- Get file metadata from WSL filesystem
- Support for multiple WSL distributions
Note: The server will only allow operations within directories specified via args
.
API
Resources
wsl -d <distrib>
: Command for operations on WSL distributions
Tools
-
read_file
- Read complete contents of a file from WSL
- Input:
path
(string) - Reads complete file contents with UTF-8 encoding
-
read_multiple_files
- Read multiple files simultaneously from WSL
- Input:
paths
(string[]) - Failed reads won't stop the entire operation
-
write_file
- Create new file or overwrite existing in WSL (exercise caution)
- Inputs:
path
(string): File locationcontent
(string): File content
-
edit_file
- Make selective edits using advanced pattern matching and formatting in WSL files
- Features:
- Line-based and multi-line content matching
- Whitespace normalization with indentation preservation
- Multiple simultaneous edits with correct positioning
- Indentation style detection and preservation
- Git-style diff output with context
- Preview changes with dry run mode
- Inputs:
path
(string): File to editedits
(array): List of edit operationsoldText
(string): Text to search for (can be substring)newText
(string): Text to replace with
dryRun
(boolean): Preview changes without applying (default: false)
- Returns detailed diff and match information for dry runs, otherwise applies changes
-
create_directory
- Create new directory or ensure it exists in WSL
- Input:
path
(string) - Creates parent directories if needed
- Succeeds silently if directory exists
-
list_directory
- List directory contents in WSL with [FILE] or [DIR] prefixes
- Input:
path
(string)
-
directory_tree
- Get a recursive tree view of files and directories as a JSON structure
- Input:
path
(string) - Returns tree structure with name, type, and children properties
-
move_file
- Move or rename files and directories in WSL
- Inputs:
source
(string)destination
(string)
- Fails if destination exists
-
search_files
- Recursively search for files/directories in WSL
- Inputs:
path
(string): Starting directorypattern
(string): Search patternexcludePatterns
(string[]): Exclude any patterns. Glob formats are supported.
- Case-insensitive matching
- Returns full paths to matches
-
get_file_info
- Get detailed file/directory metadata from WSL
- Input:
path
(string) - Returns:
- Size
- Creation time
- Modified time
- Access time
- Type (file/directory)
- Permissions
-
list_allowed_directories
- List all directories the server is allowed to access in WSL
- No input required
-
list_wsl_distributions
- Lists all available WSL distributions and shows which one is currently being used
- No input required
Requirements
- Windows Subsystem for Linux (WSL) properly configured
- At least one Linux distribution installed in WSL
For Claude Desktop users: No additional installation required
For development:
- Node.js (v14.0.0 or higher)
- TypeScript (installed as a development dependency)
Installing Node.js on Windows
- Download the Windows installer from the official Node.js website
- Run the installer and follow the installation wizard
- Verify installation by opening Command Prompt and running:
node --version npm --version
Usage
Before running the server, you need to build the TypeScript project:
npm install
npm run build
Run the server by specifying which WSL distribution to use (optional) and which directories to expose:
node dist/index.js [--distro=distribution_name] <allowed_directory> [additional_directories...]
If no distribution is specified, the default WSL distribution will be used.
Examples
Access Ubuntu-20.04 distribution:
node dist/index.js --distro=Ubuntu-20.04 /home/user/documents
Use default distribution:
node dist/index.js /home/user/documents
Usage with Claude Desktop
Add this to your claude_desktop_config.json
:
Option 1: Using a specific WSL distribution
{
"mcpServers": {
"wsl-filesystem": {
"command": "npx",
"args": [
"-y",
"mcp-server-wsl-filesystem",
"--distro=Ubuntu-20.04",
"/home/user/documents"
]
}
}
}
Option 2: Using the default WSL distribution
{
"mcpServers": {
"wsl-filesystem": {
"command": "npx",
"args": [
"-y",
"mcp-server-wsl-filesystem",
"/home/user/documents"
]
}
}
}
In the second example, the system will use your default WSL distribution without you needing to specify it.
Differences from original project
This fork adapts the original Filesystem MCP Server to work with WSL by:
- Replacing direct Node.js filesystem calls with WSL command executions
- Adding support for selecting specific WSL distributions
- Implementing path translation between Windows and Linux formats
- Enhancing file content handling for cross-platform compatibility
- Adding specialized tools for WSL management
License
This project is a fork of the original Filesystem MCP Server created by the Model Context Protocol team.
This MCP server for WSL is licensed under the MIT License, following the original project's license. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the original project repository.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.