Skip to content
OpenRelay is in early access, and the /v1 API is stable. New capabilities ship in the changelog.
Command Line

Agents (MCP)

Serve the whole OpenRelay API to Claude and other agents over MCP with a single command.

orl mcp serve exposes the OpenRelay API as Model Context Protocol tools over stdio, so an agent can deploy VMs, read usage, and manage resources by calling tools instead of shelling out. It uses the key and org you are already logged in with, so the agent inherits your access with no extra credentials.

Add it to Claude

Register orl as an MCP server in one command:

claude mcp add openrelay -- orl mcp serve

Claude Code (and other MCP clients like Claude Desktop) can now call OpenRelay tools directly. Log in first with orl auth login so the server has a key to use.

Choose what to expose

By default orl mcp serve exposes a curated core set of tools. Widen or narrow it:

orl mcp serve --toolset vms,clusters   # core set plus these groups
orl mcp serve --all                    # every tool
orl mcp serve --all --read-only        # every read (GET) tool, nothing that writes
FlagEffect
--toolset <group>Add a tool group (repeatable or comma separated); group names are the command groups from orl --help
--allExpose every available tool
--read-onlyExpose only read (GET) tools

Keep the toolset small

Many MCP clients degrade above roughly 50 tools. Prefer --toolset over --all so the agent sees a focused, relevant set. Use --read-only when you want an agent that can inspect but never change anything.

How access works

The agent acts as you: the tools run against the organization your key is bound to, with that key's scopes. Destructive tools (terminating a VM, spending from balance) are marked as such so a client can gate them. To give an agent a narrower footprint, log in with a key that has fewer scopes, or serve --read-only.

On this page