Arc MCP Server
Simplifies framework deployments on various hosting environments, with a focus on shared hosting.
Arc MCP Server
A Model Context Protocol (MCP) server that simplifies framework deployments on various hosting environments, with a focus on shared hosting.
Overview
Arc bridges the gap between Large Language Models (LLMs) and hosting environments, allowing novice developers to deploy web applications easily through conversational interfaces. It implements the Model Context Protocol (MCP) to expose tools, resources, and prompts that guide users through the deployment process.
Key Features
- Framework Support: Deploy Wasp applications with ease, with planned support for more frameworks
- Multi-Provider: Support for Netlify, Vercel, traditional shared hosting environments, and Hostm.com
- Guided Deployments: Prompts to guide users through the deployment process
- Authentication Management: Secure storage of hosting provider credentials
- Troubleshooting: Built-in tools to diagnose and fix common deployment issues
- Focused on Shared Hosting: Simplified deployment to traditional shared hosting environments
Status
This project is currently in early development. Contributions and feedback are welcome!
Getting Started
Prerequisites
- Python 3.10+
- MCP Client (e.g., Claude Desktop)
- Hosting provider accounts as needed
Installation
# Clone the repository
git clone https://github.com/elblanco2/arc-mcp.git
cd arc-mcp
# Create a virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\\Scripts\\activate
# Install dependencies
pip install -r requirements.txt
# Install the package in development mode
pip install -e .
Configuration
Create a .env
file with your configuration:
SECURE_STORAGE_PATH=~/.arc/credentials
Usage
Running from command line
# Start the server directly
arc
# With debug logging
arc --debug
# With a custom storage path
arc --secure-storage-path=/path/to/credentials
Using with Claude Desktop
-
Edit your Claude Desktop configuration file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%\\Claude\\claude_desktop_config.json
- macOS:
-
Add Arc server configuration:
{
"mcpServers": {
"arc": {
"command": "python",
"args": [
"-m",
"arc",
"--debug"
]
}
}
}
-
Restart Claude Desktop.
-
Start conversations with Claude about deploying your applications!
Architecture
Arc is built on a modular architecture:
- Credentials Manager: Securely stores and retrieves provider credentials
- Framework Handlers: Framework-specific deployment logic
- Hosting Providers: Provider-specific deployment operations
- MCP Interface: Exposes tools, resources, and prompts via the Model Context Protocol
Supported Providers
Provider | Status | Features |
---|---|---|
Netlify | ✅ Complete | Serverless, Edge, Forms |
Vercel | ✅ Complete | Serverless, Edge, Analytics |
Shared Hosting | ✅ Complete | SSH/SFTP, PHP, MySQL |
Hostm.com | ✅ Complete | Shared Hosting, API Access |
Supported Frameworks
Framework | Status | Features |
---|---|---|
Wasp | ✅ Complete | Full-Stack JS Framework |
Next.js | 🚧 Planned | React Framework |
Astro | 🚧 Planned | Static Site Generator |
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Development
# Install development dependencies
pip install -e ".[dev]"
# Run tests
pytest
# Run linting
flake8
License
This project is licensed under the MIT License - see the LICENSE file for details.
Acknowledgments
- Model Context Protocol for enabling this integration
- Wasp for the excellent framework used in our initial support
Related Servers
Remote MCP Server on Cloudflare
A self-hostable MCP server for Cloudflare Workers with OAuth login support, using Cloudflare KV for storage.
Vidu MCP
Access Vidu's latest video generation models via the Model Context Protocol (MCP).
Cloud Analyzer
A server for analyzing cloud infrastructure and services, with local testing support via Localstack.
AWS Knowledge Base Retrieval
Retrieve information from an AWS Knowledge Base using the Bedrock Agent Runtime.
Rowan
An MCP server for the Rowan computational chemistry platform.
RAD Security
Interact with the RAD Security platform which provides AI-powered security insights for Kubernetes and cloud environments.
Simple OpenStack MCP
Execute OpenStack CLI commands using LLMs. Requires a configured OpenStack CLI environment.
CData LinkedIn Ads
MCP Server for LinkedIn Ads, powered by the CData JDBC Driver. Requires a separate license and configuration.
MCP Kubernetes Server
Control Kubernetes clusters through interactions with Large Language Models (LLMs).
Remote MCP Server (Authless)
A template for deploying a remote, authentication-free MCP server on Cloudflare Workers.