6amdev-server-mcp
OfficialProvides tools for managing Docker containers, including start, stop, restart, logs, exec, stats, and image listing.
Allows management of Git repositories and issues on a Gitea instance, including listing repos, viewing repo info, managing issues, and listing branches.
Provides tools to interact with local LLM models via Ollama, including listing models, running prompts, pulling new models, and viewing model info.
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., "@6amdev-server-mcp list running Docker containers"
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.
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
Related MCP server: linux-mcp-server
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-server2. Install Dependencies
npm install3. Configure Environment
cp .env.example .env
nano .env # Edit with your values4. Install Claude Code (Optional)
chmod +x scripts/install-claude-code.sh
./scripts/install-claude-code.sh5. Build & Run
npm run build
npm start6. Setup as Systemd Service (Optional)
chmod +x scripts/setup-systemd.sh
sudo ./scripts/setup-systemd.shClient 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 |
| ดูสถานะ CPU, RAM, Disk |
| ดู process ที่ทำงานอยู่ |
| ดู system logs |
| ดู uptime และ load |
Docker Tools
Tool | Description |
| แสดง containers ทั้งหมด |
| Start container |
| Stop container |
| Restart container |
| ดู container logs |
| รัน command ใน container |
| ดูสถิติ resource usage |
| แสดง images |
Gitea Tools
Tool | Description |
| List repositories |
| ดูข้อมูล repository |
| List/manage issues |
| สร้าง issue ใหม่ |
| List branches |
Ollama Tools
Tool | Description |
| แสดง models ที่มี |
| ดูสถานะ Ollama service |
| รัน prompt กับ model |
| Download model ใหม่ |
| ดูข้อมูล model |
| ลบ model |
Workspace Tools
Tool | Description |
| List projects |
| แสดงโครงสร้างโปรเจกต์ |
| อ่านไฟล์ |
| เขียนไฟล์ |
| ค้นหาไฟล์/content |
| รัน git commands |
Claude Code Tools
Tool | Description |
| ถามคำถาม Claude Code |
| สั่งให้ทำ task |
| Review code |
| อธิบายโค้ด |
| เช็คสถานะ Claude Code |
Environment Variables
Variable | Description | Default |
| Root directory for workspace |
|
| Gitea server URL |
|
| Gitea API token | - |
| Ollama API URL |
|
| Claude API key | - |
| Logging level |
|
Development
# Run in development mode (auto-reload)
npm run dev
# Build
npm run build
# Lint
npm run lintLicense
MIT © 6AMDev
Available Tools
34 toolsclaude_askC
Ask Claude Code a question about code, architecture, or development. Returns AI-generated response.
Inputs: question (required), project.
claude_explainB
Ask Claude Code to explain how specific code or a feature works
Inputs: target (required), project (required).
claude_reviewB
Ask Claude Code to review code and provide feedback
Inputs: project (required), files, focus.
claude_statusB
Check if Claude Code CLI is installed and working
Inputs: no named parameters.
claude_taskB
Give Claude Code a task to complete (e.g., write code, refactor, fix bug). Claude will modify files directly.
Inputs: task (required), project (required), files.
docker_execB
Execute a command inside a running container
Inputs: command (required), container (required).
docker_imagesC
List Docker images
Inputs: no named parameters.
docker_listB
List all Docker containers
Inputs: all.
docker_logsB
View logs from a Docker container
Inputs: container (required), lines, follow.
docker_restartB
Restart a Docker container
Inputs: container (required).
docker_startC
Start a Docker container
Inputs: container (required).
docker_statsB
Show resource usage statistics for containers
Inputs: no named parameters.
docker_stopC
Stop a Docker container
Inputs: container (required).
gitea_branchesA
List branches in a repository
Inputs: repo (required), owner (required).
gitea_create_issueB
Create a new issue in a repository
Inputs: repo (required), owner (required), title (required), body.
gitea_issuesC
List issues in a repository
Inputs: repo (required), owner (required), state.
gitea_repo_infoC
Get detailed information about a repository
Inputs: repo (required), owner (required).
gitea_reposC
List all repositories from Gitea
Inputs: owner.
ollama_deleteB
Delete an Ollama model
Inputs: model (required).
ollama_infoB
Get detailed information about a specific model
Inputs: model (required).
ollama_listA
List all available Ollama models
Inputs: no named parameters.
ollama_pullA
Download/pull a new model from Ollama registry
Inputs: model (required).
ollama_runC
Run a prompt with an Ollama model
Inputs: model (required), prompt (required), system.
ollama_statusA
Check if Ollama service is running
Inputs: no named parameters.
system_logsC
View system logs for a specific service
Inputs: service (required), lines.
system_processesB
List running processes, optionally filtered by name
Inputs: limit, filter.
system_statusA
Get current system status including CPU, RAM, and Disk usage
Inputs: no named parameters.
system_uptimeA
Get system uptime and load average
Inputs: no named parameters.
workspace_gitB
Run git commands in a project directory
Inputs: path (required), command (required).
workspace_listB
List all projects in the workspace directory
Inputs: no named parameters.
workspace_readB
Read contents of a file in the workspace
Inputs: path (required).
workspace_searchC
Search for files or content in the workspace
Inputs: query (required), path, type.
workspace_treeA
Show directory tree structure of a project
Inputs: path, depth.
workspace_writeB
Write content to a file in the workspace
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 34 tools
Tools are grouped by domain (system, docker, gitea, ollama, workspace, claude) which makes them fairly distinct. However, the system_* and docker_* tools have some overlap in purpose (e.g., system_status vs docker_stats both report resource usage), which could cause minor confusion for an agent.
All tool names use a consistent pattern of domain_prefix_action (e.g., docker_list, gitea_issues). This makes the set predictable. Minor inconsistency: the workspace tools use git as part of workspace_git rather than git_*, and claude tools are not prefixed uniformly (e.g., claude_ask vs claude_status).
With 34 tools, the server covers six domains, but this is on the heavy side for a single server. The claude and ollama domains add 5-6 tools each which feels excessive given that many tasks could be combined (e.g., claude_ask, claude_task, claude_review, claude_explain all serve similar purposes with vague boundaries).
Each domain has reasonable coverage: system has monitoring, docker has basic lifecycle, gitea has listing and issue creation, ollama has model management. Notable gaps: gitea lacks repo creation/update/deletion and commit reading; workspace lacks file deletion or listing by type; no tool for restarting services or managing users.
Maintenance
Related MCP Connectors
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
MCP server for Gainium — manage trading bots, deals, and balances via AI assistants
Remote MCP server for supportsheep: run AI interviews and manage support content for your blog.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceMCP server enabling AI assistants to securely operate remote servers via persistent SSH sessions, with tools for command execution, file transfer, directory listing, and system monitoring.4MIT
- AlicenseBqualityDmaintenanceAn MCP server for managing Ubuntu/Linux systems, enabling AI assistants to execute commands, manage services, files, logs, and packages via local or SSH connection.47MIT
- AlicenseNot gradedqualityFmaintenanceA comprehensive MCP server integrating OpenAI GPT models for AI-powered tasks like code analysis, generation, and translation, along with system utilities, Docker management, network diagnostics, and web tools.MIT
- FlicenseNot gradedqualityDmaintenanceMCP server for remote Linux server administration via SSH, integrating with Claude Code to manage Ubuntu/Debian servers.2-