6amdev-server-mcp
MCP server for managing Ubuntu servers with AI integration, enabling system monitoring, Docker control, Gitea repository management, Ollama LLM interaction, workspace file operations, and Claude Code assistant via natural language.
README
6AMDev MCP Server
MCP (Model Context Protocol) Server สำหรับจัดการ Ubuntu Server พร้อม AI Integration
Features
- System Management: ดู CPU, RAM, Disk, Processes, Logs
- Docker Control: จัดการ containers (start, stop, logs, exec)
- Gitea Integration: จัดการ Git repositories และ Issues
- Ollama Tools: ควบคุม Local LLM models
- Workspace Management: จัดการไฟล์และโปรเจกต์
- Claude Code Integration: AI-powered coding assistant
Architecture
┌─────────────────┐ MCP Protocol ┌─────────────────────────────────┐
│ Windows PC │◄────────────────────► │ Ubuntu Server (192.168.80.203) │
│ (Cursor/Claude)│ (stdio) │ │
└─────────────────┘ │ ┌─────────────────────────────┐│
│ │ MCP Server (Node.js) ││
│ │ - System Tools ││
│ │ - Docker Tools ││
│ │ - Gitea Tools ││
│ │ - Ollama Tools ││
│ │ - Workspace Tools ││
│ │ - Claude Code Tools ││
│ └─────────────────────────────┘│
└─────────────────────────────────┘
Quick Start
1. Clone Repository
cd ~/workspace
git clone http://192.168.80.203:3000/wit/6amdev-mcp-server.git
cd 6amdev-mcp-server
2. Install Dependencies
npm install
3. Configure Environment
cp .env.example .env
nano .env # Edit with your values
4. Install Claude Code (Optional)
chmod +x scripts/install-claude-code.sh
./scripts/install-claude-code.sh
5. Build & Run
npm run build
npm start
6. Setup as Systemd Service (Optional)
chmod +x scripts/setup-systemd.sh
sudo ./scripts/setup-systemd.sh
Client Configuration
Cursor / Claude Desktop
Add to your MCP configuration file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"6amdev": {
"command": "ssh",
"args": ["-tt", "wit@192.168.80.203", "cd ~/workspace/6amdev-mcp-server && node dist/index.js"]
}
}
}
Available Tools
System Tools
| Tool | Description |
|---|---|
system_status |
ดูสถานะ CPU, RAM, Disk |
system_processes |
ดู process ที่ทำงานอยู่ |
system_logs |
ดู system logs |
system_uptime |
ดู uptime และ load |
Docker Tools
| Tool | Description |
|---|---|
docker_list |
แสดง containers ทั้งหมด |
docker_start |
Start container |
docker_stop |
Stop container |
docker_restart |
Restart container |
docker_logs |
ดู container logs |
docker_exec |
รัน command ใน container |
docker_stats |
ดูสถิติ resource usage |
docker_images |
แสดง images |
Gitea Tools
| Tool | Description |
|---|---|
gitea_repos |
List repositories |
gitea_repo_info |
ดูข้อมูล repository |
gitea_issues |
List/manage issues |
gitea_create_issue |
สร้าง issue ใหม่ |
gitea_branches |
List branches |
Ollama Tools
| Tool | Description |
|---|---|
ollama_list |
แสดง models ที่มี |
ollama_status |
ดูสถานะ Ollama service |
ollama_run |
รัน prompt กับ model |
ollama_pull |
Download model ใหม่ |
ollama_info |
ดูข้อมูล model |
ollama_delete |
ลบ model |
Workspace Tools
| Tool | Description |
|---|---|
workspace_list |
List projects |
workspace_tree |
แสดงโครงสร้างโปรเจกต์ |
workspace_read |
อ่านไฟล์ |
workspace_write |
เขียนไฟล์ |
workspace_search |
ค้นหาไฟล์/content |
workspace_git |
รัน git commands |
Claude Code Tools
| Tool | Description |
|---|---|
claude_ask |
ถามคำถาม Claude Code |
claude_task |
สั่งให้ทำ task |
claude_review |
Review code |
claude_explain |
อธิบายโค้ด |
claude_status |
เช็คสถานะ Claude Code |
Environment Variables
| Variable | Description | Default |
|---|---|---|
WORKSPACE_ROOT |
Root directory for workspace | /home/wit/workspace |
GITEA_URL |
Gitea server URL | http://localhost:3000 |
GITEA_TOKEN |
Gitea API token | - |
OLLAMA_URL |
Ollama API URL | http://localhost:11434 |
ANTHROPIC_API_KEY |
Claude API key | - |
LOG_LEVEL |
Logging level | info |
Development
# Run in development mode (auto-reload)
npm run dev
# Build
npm run build
# Lint
npm run lint
License
MIT © 6AMDev
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.