Open Resource Broker
A unified API for orchestrating and provisioning compute capacity programmatically. Define what you need in a template, request it, track it, return it — through a CLI, REST API, Python SDK, or MCP server.
What is Open Resource Broker?
Open Resource Broker is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to unified api for orchestrating and provisioning compute capacity programmatically. define what you need in a template, request it, track it, return it — through a cli, rest api, python sdk, or mcp serv...
A unified API for orchestrating and provisioning compute capacity programmatically. Define what you need in a template, request it, track it, return it — through a CLI, REST API, Python SDK, or MCP server.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A unified API for orchestrating and provisioning compute cap
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx open-resource-brokerConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Open Resource Broker
Open Resource Broker (ORB) is an AWS Labs Python package that provides a unified API for programmatically orchestrating and provisioning compute capacity through templates. It exposes a CLI, REST API, Python SDK, and MCP server interface, allowing AI assistants to request machines, track provisioning status, manage resource lifecycles, and validate infrastructure templates — all backed by AWS credentials for compute provisioning.
Prerequisites
- Python 3.10 or newer
- AWS credentials configured (via CLI profiles, environment variables, IAM instance roles, or AWS SSO)
- pip for package installation
- AWS CLI installed and 'aws sts get-caller-identity' returning successfully
- Network access to AWS APIs from the machine running the MCP server
Install orb-py
Install the Open Resource Broker Python package. Use the 'all' extra to include CLI colors, REST API server, and monitoring components.
pip install "orb-py[all]"
# Or install only what you need:
pip install orb-py # Core only
pip install "orb-py[cli]" # With colored CLI output
pip install "orb-py[api]" # With REST API serverConfigure AWS credentials
Ensure AWS credentials are configured and the account has permissions to provision compute resources. Verify the setup before proceeding.
# Option 1: AWS CLI profile
aws configure
# Option 2: Environment variables
export AWS_ACCESS_KEY_ID=your_key_id
export AWS_SECRET_ACCESS_KEY=your_secret
export AWS_DEFAULT_REGION=us-east-1
# Verify credentials work
aws sts get-caller-identityConfigure ORB directories (optional)
Customize ORB's working directories via environment variables if you need non-default paths.
export ORB_ROOT_DIR="/path/to/orb-data" # Base directory for all ORB subdirectories
export ORB_LOG_LEVEL="INFO" # DEBUG, INFO, WARNING, or ERRORStart the MCP server
Launch ORB in MCP stdio mode for use with Claude Desktop, or in TCP mode for development.
# Stdio mode (for Claude Desktop and Claude Code)
orb mcp serve --stdio
# TCP mode for development and testing
orb mcp serve --port 3000 --host localhostAdd to Claude Desktop configuration
Register the ORB MCP server in your claude_desktop_config.json.
{
"mcpServers": {
"open-resource-broker": {
"command": "orb",
"args": ["mcp", "serve", "--stdio"],
"env": {
"AWS_DEFAULT_REGION": "us-east-1",
"ORB_LOG_LEVEL": "INFO"
}
}
}
}Verify available templates
After connecting, check which compute templates are available in your ORB environment before making provisioning requests.
orb templates list
orb infrastructure showOpen Resource Broker Examples
Client configuration
claude_desktop_config.json entry for the Open Resource Broker MCP server in stdio mode with AWS region configured.
{
"mcpServers": {
"open-resource-broker": {
"command": "orb",
"args": ["mcp", "serve", "--stdio"],
"env": {
"AWS_DEFAULT_REGION": "us-east-1",
"ORB_LOG_LEVEL": "INFO"
}
}
}
}Prompts to try
Use these prompts with Claude after connecting to the ORB MCP server to manage compute resources.
- "List all available compute templates in the resource broker"
- "Request 3 machines using the 'ml-training-large' template and track the provisioning status"
- "Check the status of request req-12345"
- "Validate my template configuration before submitting a provisioning request"
- "List all currently active machine allocations and return any idle ones"
- "Show the current infrastructure health status"Troubleshooting Open Resource Broker
orb command not found after pip install
Ensure the Python scripts directory is on your PATH. Run 'pip show orb-py' to find the installation location, then add the scripts directory (e.g., ~/.local/bin on Linux/macOS) to your PATH in your shell profile.
AWS credentials error when starting the MCP server
Run 'aws sts get-caller-identity' to verify credentials are configured correctly. If using SSO, run 'aws sso login --profile your-profile' first. Ensure the IAM role or user has EC2 and relevant compute provisioning permissions.
No templates available after connecting
Run 'orb infrastructure discover' to scan your AWS environment for available infrastructure providers and templates. The ORB_ROOT_DIR must be writable and accessible. Check logs at the configured ORB_LOG_DIR for detailed error messages.
Frequently Asked Questions about Open Resource Broker
What is Open Resource Broker?
Open Resource Broker is a Model Context Protocol (MCP) server that unified api for orchestrating and provisioning compute capacity programmatically. define what you need in a template, request it, track it, return it — through a cli, rest api, python sdk, or mcp server. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Open Resource Broker?
Follow the installation instructions on the Open Resource Broker GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Open Resource Broker?
Open Resource Broker works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Open Resource Broker free to use?
Yes, Open Resource Broker is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Open Resource Broker Alternatives — Similar Cloud Services Servers
Looking for alternatives to Open Resource Broker? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Open Resource Broker in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Open Resource Broker?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.