MCP PC Control Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP PC Control Server read the contents of my todo.txt file"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP PC Control Server
A powerful Model Context Protocol (MCP) server that provides comprehensive PC control capabilities including file operations, directory management, command execution, system inspection, and process management. Designed to give AI assistants (Claude, GPT, Gemini, etc.) full, efficient control over the host machine.
Features
File Operations
read_file - Read complete file contents with proper encoding
read_file_lines - Read a specific range of lines from a file (efficient for large files)
write_file - Create new files or overwrite existing ones
append_to_file - Append content to a file without overwriting it
edit_file - Make precise text-based edits with diff output
copy_file - Copy a file to a new location (source preserved)
delete_file - Remove files from the filesystem
move_file - Move or rename files and directories
get_file_info - Get detailed file metadata (size, timestamps, permissions, readability)
Directory Operations
create_directory - Create directories (supports nested creation)
list_directory - List directory contents with detailed information
delete_directory - Recursively delete directories and their contents
search_files - Recursively search for files matching name patterns
Content Search
search_in_files - Grep-like search for text content within files, with optional file-pattern filtering and case-insensitive mode
System Operations
execute_command - Execute shell commands with optional working directory and configurable timeout
get_system_info - Get OS, CPU, memory, uptime, hostname, and network interface details
list_processes - List running processes with optional name filter
get_environment - Read environment variables (one or all)
Related MCP server: Enhanced File Operations MCP Server
Installation
Clone or download this repository
Install dependencies:
npm installBuild the project:
npm run buildUsage
Running the Server
The server communicates via stdio and is designed to be used with MCP clients:
npm startConfiguration with Claude Desktop
Add this server to your Claude Desktop configuration file:
On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"pc-control": {
"command": "node",
"args": ["/absolute/path/to/first_mcp/build/index.js"]
}
}
}Replace /absolute/path/to/first_mcp with the actual absolute path to this project directory.
Configuration with Other AI Clients
Any MCP-compatible client (Claude, Cursor, Windsurf, Continue, etc.) can connect to this server using the same stdio transport approach. Point the client at the built build/index.js with node.
Example with npx (Alternative)
{
"mcpServers": {
"pc-control": {
"command": "npx",
"args": ["-y", "mcp-pc-control-server"]
}
}
}Available Tools
read_file
{ path: string }read_file_lines
{
path: string,
start: number, // 1-based, inclusive
end?: number // 1-based, inclusive (omit to read to end)
}write_file
{ path: string, content: string }append_to_file
{ path: string, content: string }edit_file
{
path: string,
edits: [{ oldText: string, newText: string }]
}copy_file
{ source: string, destination: string }create_directory
{ path: string }list_directory
{ path: string }delete_file
{ path: string }delete_directory
{ path: string }move_file
{ source: string, destination: string }get_file_info
{ path: string }execute_command
{
command: string,
workingDirectory?: string,
timeout?: number // ms, default 30000
}search_files
{ path: string, pattern: string } // pattern supports * and **search_in_files
{
path: string,
query: string,
filePattern?: string, // e.g. "*.ts"
caseSensitive?: boolean // default false
}get_system_info
{} // no arguments requiredlist_processes
{ filter?: string } // optional substring filter on process nameget_environment
{ variable?: string } // omit to get all env varsSecurity Considerations
WARNING: This server provides powerful filesystem and command execution capabilities.
File Access: Can read, write, and delete any files the process has permissions for
Command Execution: Can execute arbitrary shell commands
No Sandboxing: Operations are not sandboxed or restricted
Recommendations:
Only use with trusted MCP clients
Run with minimal necessary permissions
Be cautious with the
execute_commandanddelete_directorytoolsConsider implementing additional access controls for production use
Review all operations in sensitive environments
Development
Build
npm run buildWatch Mode
npm run watchProject Structure
.
├── src/
│ └── index.ts # Main server implementation
├── build/ # Compiled JavaScript (generated)
├── package.json
├── tsconfig.json
└── README.mdLicense
MIT
Contributing
Contributions are welcome! Please feel free to submit issues or pull requests.
Troubleshooting
Server not appearing in Claude Desktop
Check that the path in
claude_desktop_config.jsonis absolute and correctVerify the build directory exists and contains
index.jsRestart Claude Desktop after configuration changes
Check Claude Desktop logs for errors
Permission Errors
Ensure the server process has necessary file system permissions
On Unix systems, check file/directory permissions with
ls -laRun with appropriate user privileges for the operations you need
Command Execution Issues
Verify the working directory exists and is accessible
Check that shell commands are appropriate for your operating system
Increase the
timeoutparameter for long-running commandsSome commands may require specific environment variables
Available Tools
11 toolscreate_directoryA
Create a new directory or ensure a directory exists. Can create multiple nested directories in one operation. If the directory already exists, this operation will succeed silently.
Inputs: path (required).
delete_directoryA
Permanently delete a directory and all of its contents, including all files and subdirectories. This is a recursive operation that cannot be undone. Use with extreme caution.
Inputs: path (required).
delete_fileA
Permanently delete a file from the file system. This operation cannot be undone. The file is immediately removed from the storage device.
Inputs: path (required).
edit_fileA
Make line-based edits to a text file. Provide original lines and their replacements. Returns a git-style diff showing the changes made. Each edit replaces exact line sequences with new content.
Inputs: path (required), edits (required).
execute_commandA
Execute shell commands on the system. SECURITY WARNING: This tool provides direct system access. Only use with trusted commands. Commands run with the same permissions as the MCP server process.
Inputs: command (required), workingDirectory.
get_file_infoA
Retrieve detailed metadata about a file or directory, including size, creation time, modification time, access time, type, and permissions. This does not read file contents.
Inputs: path (required).
list_directoryA
Get a detailed listing of all files and directories in a specified path. Results include names, types (file/directory), sizes, and modification times. Useful for understanding directory structure and finding files.
Inputs: path (required).
move_fileA
Move or rename files and directories. Can move files between directories and rename them in a single operation. If the destination exists, the operation will fail.
Inputs: source (required), destination (required).
read_fileA
Read the complete contents of a file from the file system. Handles various text encodings and returns the full file content. Use this to examine file contents before editing.
Inputs: path (required).
search_filesA
Recursively search for files matching a pattern in a directory. Supports wildcards (* and **) and returns matching file paths. Useful for finding files by name or extension.
Inputs: path (required), pattern (required).
write_fileA
Create a new file or completely overwrite an existing file with new content. Use with caution as it will overwrite existing files without warning. Handles text content with proper encoding.
Inputs: path (required), content (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 11 tools
Each tool has a clearly distinct purpose with no ambiguity: create_directory vs. delete_directory, read_file vs. edit_file vs. write_file, list_directory vs. search_files, etc. The descriptions reinforce unique roles, such as get_file_info for metadata only and execute_command for shell operations, preventing misselection.
All tool names follow a consistent verb_noun pattern using snake_case, such as create_directory, delete_file, and execute_command. This predictable naming scheme makes it easy for agents to understand and use the tools without confusion from mixed conventions.
With 11 tools, the server is well-scoped for PC control, covering essential file system operations (CRUD for files/directories), metadata retrieval, searching, and command execution. Each tool earns its place without being overwhelming or insufficient for the domain.
The tool set provides complete coverage for file system management: create, read, edit, write, delete, move, list, search, and get info for files and directories, plus execute_command for broader system control. There are no obvious gaps, enabling agents to handle full workflows without dead ends.
Maintenance
Related MCP Connectors
Use your Mac, Windows or Linux computer from ChatGPT, Claude or Codex: files, commands, documents.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Connect ChatGPT, Claude, Cursor or VS Code to your Windows PC: files, terminal, browser, apps.
Related MCP Servers
- AlicenseDqualityDmaintenanceEnables AI models to perform file system operations (reading, creating, and listing files) on a local file system through a standardized Model Context Protocol interface.3ISC
- FlicenseNot gradedqualityCmaintenanceA comprehensive Model Context Protocol server that provides over 50 file and system management tools for AI models, including navigation, file operations, search, compression, and system information capabilities.-
- AlicenseAqualityDmaintenanceA comprehensive Model Context Protocol server that enables AI assistants to interact with and manage Windows systems, providing capabilities for file system operations, process management, system information retrieval, registry operations, service management, network diagnostics, and performance monitoring.716 npm6Apache 2.0
- AlicenseAqualityDmaintenanceEnables file management operations on the desktop including creating, reading, editing, moving, renaming, deleting, and listing files through the Model Context Protocol.6ISC