Kasm MCP Server v2
Enables AI agents to manage and interact with Kasm Workspaces containerized desktop infrastructure, providing tools for session management, command execution, file operations, and user management via the Model Context Protocol.
README
Kasm MCP Server v2
A Model Context Protocol (MCP) server that enables AI agents to manage and interact with Kasm Workspaces containerized desktop infrastructure. This server provides a standardized interface for LLMs to create, manage, and execute commands within Kasm sessions.
๐ Quick Start
# Clone the repository
git clone https://github.com/roguedev-ai/kasm-mcp-server-v2.git
cd kasm-mcp-server-v2
# Run the automated setup script
./setup-prerequisites.sh
# Choose option 1 for NPM/Python mode (recommended for Cline)
# Configure your Kasm API credentials when prompted
# Start the server
source venv/bin/activate
python -m src
๐ Documentation
- Quick Start Guide - Get up and running in 5 minutes
- Installation Guide - Detailed installation instructions
- Tool Reference - Complete reference for all 21 available tools
- Suggested Prompts - Example prompts for effective usage
- Troubleshooting Guide - Common issues and solutions
- Cline Integration Guide - Configure Cline to use this MCP server
- LLM Integration Guide - Integrate with any MCP-compatible LLM
- Architecture Documentation - System design and components
- Security Documentation - Security features and best practices
โจ Features
- ๐ง Session Management - Create, destroy, and monitor Kasm workspace sessions
- ๐ป Command Execution - Execute commands inside Kasm containers with security boundaries
- ๐ File Operations - Read and write files within Kasm sessions
- ๐ฅ User Management - Create and manage Kasm users
- ๐ Security - MCP Roots security mechanism for safe file operations
- ๐ Multiple Deployment Options - NPM/Python or Docker deployment
๐ ๏ธ Available Tools
The server provides 21 tools organized into categories:
Session Management (8 tools)
create_kasm_session- Launch a new Kasm workspacedestroy_kasm_session- Terminate a sessionget_session_status- Check session statuslist_user_sessions- List your active sessionslist_all_sessions- List all system sessions (admin)pause_kasm_session- Pause a session to free resourcesresume_kasm_session- Resume a paused sessionget_session_screenshot- Capture session screenshot
Command & File Operations (3 tools)
execute_kasm_command- Execute shell commands in sessionsread_kasm_file- Read file contents from sessionswrite_kasm_file- Write content to files in sessions
User Management (6 tools)
get_kasm_users- List all userscreate_kasm_user- Create new user accountsget_kasm_user- Get specific user detailsupdate_kasm_user- Update user informationdelete_kasm_user- Remove users from systemlogout_kasm_user- Logout all user sessions
Monitoring & Performance (3 tools)
get_session_frame_stats- Frame rendering statisticsget_session_bottleneck_stats- CPU/network bottleneck analysisget_session_recordings- Access session recordings
System Information (1 tool)
get_available_workspaces- List available workspace images
See the Tool Reference for complete details on all tools.
๐ฆ Installation Options
Option 1: Automated Setup (Recommended)
Use the setup-prerequisites.sh script for automated installation:
./setup-prerequisites.sh
Choose from:
- NPM/Python Mode - Direct execution with npm support (best for Cline)
- Docker Mode - Containerized deployment
- Both - Install prerequisites for both modes
Option 2: Manual Installation
See the Installation Guide for manual setup instructions.
๐ง Configuration
Create a .env file with your Kasm credentials:
KASM_API_URL=https://your-kasm-instance.com
KASM_API_KEY=your_api_key_here
KASM_API_SECRET=your_api_secret_here
KASM_USER_ID=default
KASM_ALLOWED_ROOTS=/home/kasm-user
LOG_LEVEL=INFO
๐งช Testing
Run the diagnostic test to verify your installation:
python test_server.py
๐ Troubleshooting
Recent Fixes
- FastMCP Initialization Error - Fixed in commit c95882e (see MCP_SDK_COMPATIBILITY_FIX.md)
- Import Issues - Resolved with official MCP SDK migration
Common Issues
- "No module named 'mcp'" - Install the MCP SDK:
pip install mcp - Environment variables not set - Check your
.envfile configuration - Server won't start - Run
python test_server.pyfor diagnostics
๐ค Contributing
Contributions are welcome! Please read our contributing guidelines and submit pull requests to the repository.
๐ License
This project is licensed under the MIT License - see the LICENSE file for details.
๐ Resources
๐ง Support
For issues and questions:
- Open an issue on GitHub
- Check existing documentation in the
/docsfolder - Review the troubleshooting section above
Current Version: 2.0.1
Last Updated: September 10, 2025
Status: โ
Production Ready
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.