What are the prerequisites for using MCP Fly Deployer?
Python 3.13 or higher, `pip`, the Fly.io CLI installed and configured, and Node.js with npm (for supergateway functionality).
@NakulRajan
基本信息
MCP server that provides docker files for stdio based MCP server to be deployed on platform like Fly.IO
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-fly-deployer": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
MCP Fly Deployer is a configuration generator that automates Dockerfiles, fly.toml files, and deployment scripts for deploying stdio-based Model Context Protocol (MCP) servers to Fly.io. It integrates supergateway to convert stdio MCP servers into SSE or WebSocket services for remote access.
Clone the repository, create and activate a Python virtual environment, and install dependencies with uv sync. Start the server by running python mcp_server_generator.py (listens on port 8000 via SSE transport), then send a request with parameters such as server_command, server_args, runtime, runtime_version, and optional settings like target_port, app_name, and primary_region.
fly.toml configurationPython 3.13 or higher, `pip`, the Fly.io CLI installed and configured, and Node.js with npm (for supergateway functionality).
It uses supergateway to convert stdio-based MCP servers into SSE or WebSocket services, handle JSON-RPC versioning automatically, and manage package metadata transmission.
Python, Node.js, Go, and custom binary (`binary`). Runtime versions can be specified (e.g., Node.js 20).
The server uses SSE transport and listens on port 8000 by default.
Yes, use the `primary_region` parameter. Common regions include `ord` (Chicago), `iad` (Northern Virginia), `dfw` (Dallas), `lax` (Los Angeles), and `bom` (Mumbai).
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Hindsight: Agent Memory That Learns
A curated list of references for MLOps
Open-source MCP to use Blender with any LLM
评论