bizflycloud
A Model Context Protocol (MCP) server implementation that connects to Bizfly Cloud to manage cloud resources
claude mcp add --transport stdio bizflycloud-bizflycloud-mcp-server /absolute/path/to/bizfly-mcp-server \ --env BIZFLY_REGION="HaNoi" \ --env BIZFLY_PASSWORD="your_password" \ --env BIZFLY_USERNAME="your_username"
How to use
Bizfly Cloud MCP Server provides a unified MCP interface to manage Bizfly Cloud resources (servers, volumes, load balancers, Kubernetes, databases, DNS, CDN, KMS, container registries, auto-scaling, alerts, and more). It exposes a set of prefixed tools under the bizflycloud_ namespace that let you list, get, create, update, and delete resources across multiple Bizfly Cloud services. The server is designed to work with MCP clients like Cursor and Claude Desktop, enabling them to query and control cloud resources through your local development environment or within an automation pipeline. To connect, run the MCP server binary with the required credentials and region, and point your MCP client to the server executable.
Once running, you can invoke commands such as bizflycloud_list_servers, bizflycloud_create_volume, bizflycloud_list_kubernetes_clusters, or bizflycloud_create_loadbalancer to perform common cloud operations. The tools cover a wide range of services, including compute (servers), storage (volumes, snapshots), networking (load balancers, DNS), Kubernetes, databases, and security (KMS). The configuration supports multiple regions and API endpoints through environment variables, enabling multi-region deployments and failover scenarios.
How to install
Prerequisites
- A Bizfly Cloud account with API access
- Go toolchain installed (for building from source) if you are developing locally
- MCP client (Cursor or Claude Desktop) installed on your client machine
Option A: Build from source (local development)
- Clone the repository
git clone https://github.com/your-username/bizflycloud-mcp-server.git
cd bizflycloud-mcp-server
- Ensure dependencies are downloaded
go mod download
- Build the server binary
go build -o bizfly-mcp-server
- Run the server (provide credentials via environment variables)
export BIZFLY_USERNAME=your_username
export BIZFLY_PASSWORD=your_password
export BIZFLY_REGION=HaNoi
./bizfly-mcp-server
Option B: Docker Deployment (recommended for isolation)
- Create a Dockerfile (or use the provided image if available) and build
# Example Docker build command if you have a Dockerfile
docker build -t bizfly-mcp-server:latest .
- Run the container with required env vars
docker run -it --rm \
-e BIZFLY_USERNAME=your_username \
-e BIZFLY_PASSWORD=your_password \
-e BIZFLY_REGION=HaNoi \
bizfly-mcp-server:latest
Option C: Using with MCP clients (Cursor/Claude Desktop)
- Install the MCP client and configure it to point to your server executable, providing the same environment variables as above. For Cursor, add a config entry like:
{
"mcpServers": {
"bizfly": {
"command": "/absolute/path/to/bizfly-mcp-server",
"env": {
"BIZFLY_USERNAME": "your_username",
"BIZFLY_PASSWORD": "your_password",
"BIZFLY_REGION": "HaNoi"
}
}
}
}
Additional notes
Environment variables are the primary method for credentials and region configuration. Ensure BIZFLY_PASSWORD is kept secure and not committed to source control. The server supports multiple Bizfly Cloud services, so you can enable regional endpoints by adjusting BIZFLY_REGION and BIZFLY_API_URL if needed. If you encounter authentication errors, double-check that the credentials have API access rights and that the region matches your Bizfly Cloud account. For Docker deployments, ensure Docker is configured to access your registry and that you have network access to Bizfly Cloud endpoints.
Related MCP Servers
trpc-agent-go
trpc-agent-go is a powerful Go framework for building intelligent agent systems using large language models (LLMs) and tools.
station
Station is our open-source runtime that lets teams deploy agents on their own infrastructure with full control.
tiger-cli
Tiger CLI is the command-line interface for Tiger Cloud. It includes an MCP server for helping coding agents write production-level Postgres code.
gopls
MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.
kubernetes
A Model Context Protocol (MCP) server for the Kubernetes API.
gcp-cost
💰 An MCP server that enables AI assistants to estimate Google Cloud costs, powered by Cloud Billing Catalog API and built with Genkit for Go