MCP File Server
MCP server for reading and writing local files
abhishekloiwal
README
MCP File Server
An MCP server for reading and writing files from your local file system. This server can be used with Claude for Desktop or any other MCP client to provide file system access for AI assistants.
Features
- List files and directories
- Read file contents
- Write content to files
- Delete files and directories
Prerequisites
- Docker installed on your system
- Git (optional, for cloning the repository)
Setup and Deployment
Option 1: Using Docker Compose (Recommended)
-
Clone this repository:
git clone https://github.com/abhishekloiwal/mcp-file-server.git cd mcp-file-server
-
Edit the
docker-compose.yml
file to update the volume mount path if needed. By default, it's set to:volumes: - /Users/abhishekloiwal/CascadeProjects/ClaudeProjects:/data
Replace with your desired local path if different.
-
Deploy with Docker Compose:
docker-compose up -d
Option 2: Using Docker directly
-
Clone the repository:
git clone https://github.com/abhishekloiwal/mcp-file-server.git cd mcp-file-server
-
Build the Docker image:
docker build -t mcp-file-server .
-
Run the container with your local directory mounted:
docker run -d --name mcp-file-server -v /Users/abhishekloiwal/CascadeProjects/ClaudeProjects:/data mcp-file-server
Replace the path with your desired local directory path.
Connecting to Claude for Desktop
-
Create or update your Claude for Desktop configuration file at:
- Mac:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%AppData%\Claude\claude_desktop_config.json
- Mac:
-
Add the mcp-file-server to your configuration:
{ "mcpServers": { "file-server": { "command": "docker", "args": ["exec", "-i", "mcp-file-server", "python", "server.py"] } } }
-
Restart Claude for Desktop.
-
You should now see the file-server tools available in Claude.
Available Tools
The following tools are available through this MCP server:
list_files
: List all files in a directoryread_file
: Read the contents of a filewrite_file
: Write content to a filedelete_file
: Delete a file or directory
License
MIT
Troubleshooting
-
If Claude for Desktop doesn't connect to the server, check the Docker container status:
docker ps -a | grep mcp-file-server
-
View server logs:
docker logs mcp-file-server
-
Make sure the volume is correctly mounted:
docker inspect mcp-file-server | grep -A 10 Mounts
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.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.