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 serveClaude 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| Flag | Effect |
|---|---|
--toolset <group> | Add a tool group (repeatable or comma separated); group names are the command groups from orl --help |
--all | Expose every available tool |
--read-only | Expose 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.