About Infrastructure Auto Provisioner
AutoProvisioner MCP Server is a ZeroSync infrastructure provisioning service with remote and local deployment options. The README describes installation and connection methods but does not specify its provisioning capabilities.
Key features
- 01Remote SSE communication
- 02Local stdio communication
- 03Installation script available
- 04Build from source
Use cases
- 01Connecting to MCP over remote SSE
- 02Running the service locally over stdio
- 03Compiling the service from source
MCP support
This MCP server connects to MCP clients over remote SSE or local stdio transport.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAutoProvisioner MCP Server (open beta)
Installation
- Remote (Recommended)
- requires node and npm to be installed
- remote, SSE-based communication
Update configuration as follows:
{
"mcpServers": {
"autoprovisioner": {
"command": "npx",
"args": [
"mcp-remote",
"https://autoprovisioner-remote.zerosync.co/sse"
]
}
}
}
- Local
- no system dependencies
- local, stdio-based communication
Step 1:
curl -fsSL https://raw.githubusercontent.com/zerosync-co/mcp-server-autoprovisioner/main/install-prerelease.sh | bash
Step 2:
Run mcp-server-autoprovisioner init, or update configuration as follows
{
"mcpServers": {
"autoprovisioner": {
"command": "path/to/mcp-server-autoprovisioner", // which mcp-server-autoprovisioner
"args": [
"run",
"user_..." // mcp-server-autoprovisioner whoami
]
}
}
}
Build From Source
deno compile \
--output mcp-server-autoprovisioner \
--env-file=".env" \
--no-check \
-A stdio/index.ts
Testing options
npx @modelcontextprotocol/inspector
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.