MCP Sinstaller
M

MCP Sinstaller

The MCP Secure Installer is an automated tool used to install and containerize the MCP server from a GitHub repository. It utilizes the MCP sampling function to analyze the repository and create the corresponding Docker image.
2.5 points
5.0K

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

🚀 MCP Secure Installer (mcp-sinstaller)

This project offers an MCP server installer capable of automatically installing and containerizing other MCP servers from GitHub repositories. It leverages the Model Context Protocol (MCP) sampling feature to analyze repositories and create appropriate Docker images.

View related image

📦 Installation

Requirements

  • Docker
  • MCP Client with Sampling enabled

Enable Sampling in VS Code Insiders (Recommended)

Add the following to your VS Code settings:

"chat.mcp.serverSampling": {
    "Global in Code - Insiders: sampling": {
        "allowedDuringChat": true
    }
}

💻 Usage Examples

Running the Server in VS Code (Recommended)

Basic Usage

First, clone the repository:

git clone https://github.com/semcp/mcp-sinstaller.git

Then, add the following to your VS Code settings:

"mcp-sinstaller": {
    "type": "stdio",
    "command": "uvx",
    "args": [
            "--from",
            "/path/to/mcp-sinstaller",
            "python",
            "/path/to/mcp-sinstaller/mcp_installer.py"
    ]
}

📚 Documentation

Server Naming & Multiple Servers

The installer employs a structured naming scheme: owner-repo-servername to prevent conflicts when installing multiple servers from the same repository.

Examples:

  • https://github.com/modelcontextprotocol/servers/tree/main/src/fetchmodelcontextprotocol-servers-fetch
  • https://github.com/modelcontextprotocol/servers/tree/main/src/filesystemmodelcontextprotocol-servers-filesystem
  • https://github.com/github/github-mcp-servergithub-github-mcp-server

This naming convention enables you to install multiple MCP servers from repositories like modelcontextprotocol/servers without naming conflicts.

Example (GitHub MCP Server)

Prompt: "install https://github.com/github/github-mcp-server"

GitHub Copilot:
I'll install the GitHub MCP server from the repository you specified.

sampling (MCP Server):

Input:
{
  "url": "https://github.com/github/github-mcp-server"
}

Output:
Successfully built Docker image for MCP server 'github-mcp-server'!

Repository: https://github.com/github/github-mcp-server
Location: /Users/mossaka/.mcp-installer/servers/github-mcp-server

DOCKER IMAGE:
- Using existing Dockerfile
- Image: mcp-installer-github-mcp-server
- Size & Created: REPOSITORY:TAG                           SIZE      CREATED AT
mcp-installer-github-mcp-server:latest   59.5MB    2025-06-09 14:52:46 -0700 PDT
- Ports: {}
- Environment Variables: ['GITHUB_PERSONAL_ACCESS_TOKEN', 'GITHUB_TOOLSETS', 'GITHUB_DYNAMIC_TOOLSETS', 'GITHUB_READ_ONLY', 'GITHUB_HOST']
- Required Secrets: ['GITHUB_PERSONAL_ACCESS_TOKEN']
- Metadata: /Users/mossaka/.mcp-installer/servers/github-mcp-server/metadata.json


TO RUN THE CONTAINER (STDIO Transport):

1. Set required environment variables (if any):
export GITHUB_PERSONAL_ACCESS_TOKEN=your_actual_github_personal_access_token_here

2. Run the container interactively:
   docker run -i --rm --name mcp-github-mcp-server-container -e GITHUB_PERSONAL_ACCESS_TOKEN=GitHub personal access token (required) -e GITHUB_TOOLSETS=Comma-separated list of toolsets to enable (optional) -e GITHUB_DYNAMIC_TOOLSETS=Set to 1 to enable dynamic tool discovery (optional) -e GITHUB_READ_ONLY=Set to 1 to enable read-only mode (optional) -e GITHUB_HOST=Custom GitHub API endpoint for GitHub Enterprise (optional) -e GITHUB_PERSONAL_ACCESS_TOKEN=${GITHUB_PERSONAL_ACCESS_TOKEN} mcp-installer-github-mcp-server
   
   Note: This server uses STDIO transport (stdin/stdout communication).
   - The container runs interactively (-i flag)
   - It will be automatically removed when it exits (--rm flag)
   - No port mapping needed as it uses standard input/output

3. To stop the container:
   Ctrl+C in the terminal where it's running

4. For background operation with MCP client:
   Use your MCP client to connect via subprocess/stdio


Great! The GitHub MCP server has been successfully installed. The installation completed successfully and built a Docker image.

Here's what was installed:

Server Name: github-mcp-server
Repository: https://github.com/github/github-mcp-server
Docker Image: mcp-installer-github-mcp-server:latest (59.5MB)
Transport Type: STDIO (communicates via standard input/output)
Required Configuration: The server requires a GITHUB_PERSONAL_ACCESS_TOKEN environment variable to authenticate with GitHub's API.

Optional Environment Variables:

GITHUB_TOOLSETS: Comma-separated list of toolsets to enable
GITHUB_DYNAMIC_TOOLSETS: Set to 1 to enable dynamic tool discovery
GITHUB_READ_ONLY: Set to 1 to enable read-only mode
GITHUB_HOST: Custom GitHub API endpoint for GitHub Enterprise
The server is now ready to use. To run it, you'll need to set your GitHub personal access token and then run the Docker container with the STDIO transport for communication with MCP clients.

After that, you can run docker to run the container in your agent's MCP settings.

VS Code Configuration

"github": {
    "type": "stdio",
    "command": "docker",
    "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "GITHUB_PERSONAL_ACCESS_TOKEN=<PAT>",
        "mcp-installer-github-mcp-server"
    ]
}

Example (fetch server)

Prompt: "install https://github.com/modelcontextprotocol/servers/tree/typescript-servers-0.6.2/src/fetch"

I'll install the fetch MCP server from the specific path you provided.

sampling (MCP Server)

Input:
{
  "url": "https://github.com/modelcontextprotocol/servers/tree/typescript-servers-0.6.2/src/fetch"
}

Output:
Successfully built Docker image for MCP server 'modelcontextprotocol-servers-fetch'!

Repository: https://github.com/modelcontextprotocol/servers/tree/typescript-servers-0.6.2/src/fetch
Location: /Users/mossaka/.mcp-sinstaller/servers/modelcontextprotocol-servers-fetch

DOCKER IMAGE:
- Generated new Dockerfile
- Image: mcp-sinstaller-modelcontextprotocol-servers-fetch
- Size & Created: REPOSITORY:TAG                                             SIZE      CREATED AT
mcp-sinstaller-modelcontextprotocol-servers-fetch:latest   654MB     2025-06-09 16:28:35 -0700 PDT
- Ports: {}
- Environment Variables: []
- Required Secrets: []
- Metadata: /Users/mossaka/.mcp-sinstaller/servers/modelcontextprotocol-servers-fetch/metadata.json


TO RUN THE CONTAINER (STDIO Transport):

1. Set required environment variables (if any):
   No secrets required

2. Run the container interactively:
   docker run -i --rm --name mcp-modelcontextprotocol-servers-fetch-container mcp-sinstaller-modelcontextprotocol-servers-fetch
   
   Note: This server uses STDIO transport (stdin/stdout communication).
   - The container runs interactively (-i flag)
   - It will be automatically removed when it exits (--rm flag)
   - No port mapping needed as it uses standard input/output

3. Use your MCP client to connect via subprocess/stdio transport


✅ Fetch MCP Server installed successfully!

The server has been built and is ready to use. Here are the key details:

Server Information:

Name: modelcontextprotocol-servers-fetch
Repository: https://github.com/modelcontextprotocol/servers/tree/typescript-servers-0.6.2/src/fetch
Transport: STDIO (standard input/output)
Image Size: 654MB

VS Code Configuration

"fetch": {
    "type": "stdio",
    "command": "docker",
    "args": [
        "run",
        "-i",
        "--rm",
        "mcp-sinstaller-modelcontextprotocol-servers-fetch"
    ]
}

Alternatives

R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
7.9K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
9.5K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
6.2K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
9.8K
5 points
R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
7.6K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
9.7K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
8.8K
4 points
U
Uniprof
Uniprof is a tool that simplifies CPU performance analysis. It supports multiple programming languages and runtimes, does not require code modification or additional dependencies, and can perform one-click performance profiling and hotspot analysis through Docker containers or the host mode.
TypeScript
7.3K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
30.4K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
19.2K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
63.1K
4.3 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
22.0K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
28.2K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
58.4K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
19.0K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
41.8K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase