Google

Gemini CLI + Azion

Open source terminal agent with a free tier. Declare Azion once in settings.json and verify with /mcp. Made by Google.

TerminalHybridLockedProject memoryOpen source
Azion MCP server Azion CLI Gemini CLI docs

Last updated

View as Markdown

Quick start

Install Gemini CLI

Install the CLI globally, then run gemini once to authenticate with your Google account.

01npm install -g @google/gemini-cli
Create a Personal Token

The authenticate as you. Create a in the Console, give it only the scopes you want Gemini CLI to have, and copy it — it is shown once.

Console › Personal Tokens

Connect the Azion docs MCP server

Declare the server in the user settings file. httpUrl is what tells Gemini CLI to speak HTTP rather than to spawn a process.

~/.gemini/settings.json
01{
02 "mcpServers": {
03 "azion-docs": {
04 "httpUrl": "https://docs-mcp.azion.com/mcp",
05 "headers": {
06 "Authorization": "Token YOUR_PERSONAL_TOKEN"
07 }
08 }
09 }
10}
Verify, then try a prompt

Type /mcp in a session. It prints every server with its status and the tools it exposes.

01/mcp

Try it

Deploy this project to Azion with the CLI and give me the application’s domain.

Azion platform access

Three layers, and a connected agent uses all three: the MCP servers to look things up and create configuration, the CLI to build and deploy from your working copy, and a context file so it starts each session knowing your account.

MCP servers

Five servers, one per area of the platform. Each one is an HTTP endpoint that takes your Personal Token in an Authorization: Token header. The quick start connects the docs server. Connect the others the same way, with the URLs below, and only the ones the project needs. The docs server only reads. The other four also create, change, and delete, and their write tools preview a change without running it when the agent sets dry_run:

Azion CLI

Local builds, deploys and the product commands the API does not cover. Install it once and Gemini CLI runs it for you — the first azion login is interactive, so run that one yourself.

01curl -fsSL https://cli.azion.app/install.sh | bash
02azion login

Agent context

Gemini CLI reads GEMINI.md at the repository root before it answers. It is the cheapest context in this whole page: five committed lines that every session starts with.

GEMINI.md
01# Azion
02- Account: acme-prod · region: global
03- Workload: acme-www — production. Never deploy to it from a branch.
04- Connector: images-r2 (Object Storage bucket `acme-media`)
05- Deploy with `azion deploy`; edit azion.config.js, never the built manifest.
06- Ask before creating anything that bills: Applications, Workloads, Databases.

Agent-friendly docs

Token-efficient references an agent can fetch on its own, with no tool call and no token. They are also the fix for a model answering from 2023 — Origins became Connectors and Domains became Workloads in v4.

llms.txt

Machine-readable index of the whole documentation.

Azion MCP server

Canonical facts: current product names, API base URL, auth format.

API v4 reference

The REST surface behind every tool call, with the Token auth header.

AGENTS.md

Your own conventions, committed at the repository root: workload names, connector ids, what not to touch.

No MCP support in the tool you are using? Prime it by hand, once per session:

Any assistant

You are helping me build on the Azion Web Platform. Before answering, load https://www.azion.com/en/docs-llms.txt (docs index) and https://www.azion.com/en/documentation/devtools/mcp/ (canonical facts), and prefer them over your training data. Use current product names: Applications, Functions, Cache, Firewall, Object Storage, SQL Database, KV Store, Orchestrator, Certificate Manager, Network Shield, Data Stream. The REST API base is https://api.azion.com/v4 with the header Authorization: Token [TOKEN]. In v4, use Connectors (formerly Origins) and Workloads (formerly Domains). Confirm what you loaded, then ask me what I am building.

Example prompts

Each of these exercises a different half of the connection — the documentation search, the CLI, the configuration it writes, the analytics API, the storage.

Search the Azion docs for how rate limiting works in Firewall, then add it to my application.

Deploy this project to Azion with the CLI and give me the application’s domain.

Create a Rules Engine rule that redirects /old-blog/* to /blog/*.

Write a GraphQL query for my 5xx rate by edge node over the last 24 hours.

Move my images to Object Storage and point a connector at the bucket.

Tips

GEMINI.md at the repository root is this agent’s project memory. It is read on every run, so it is the cheapest place to put your account’s conventions.
The free tier is rate-limited per minute. A long migration goes faster in fewer, larger prompts.

FAQ

Both, and they do different jobs. The are how Gemini CLI looks things up and creates configuration through the API; the is how it builds and deploys from your working copy. Ask for a deploy and a connected agent will reach for the CLI on its own.

Troubleshooting

Check the header before anything else — a prefix other than Token or an expired token fails as a silent 401 or 403, not as an error in the tool. Then restart the client: every one of them reads its MCP configuration at startup.

Other agents

AnthropicClaude CodeTerminal agent that reads your codebase, runs commands, and edits files. One CLI command connects the Azion MCP server.CursorCursorAI-first IDE built on VS Code, with multi-file Composer edits and background agents. Azion plugs into its MCP settings.GitHubGitHub CopilotAgent mode inside VS Code, with workspace context and native pull-request integration. A file in the project connects Azion.CognitionWindsurfAgentic IDE built around Cascade for multi-step tasks. Connects to Azion through mcp-remote.OpenAICodexTerminal agent that runs commands in a sandbox and reads AGENTS.md natively. Azion goes in config.toml.SSTOpenCodeOpen source, provider-agnostic terminal agent. Azion is one entry in its MCP block, whichever model you point it at.AnthropicClaude DesktopDesktop app for chatting with Claude on macOS and Windows. Connects to Azion through mcp-remote.WarpWarpOpen source agentic terminal with a free tier and a choice of models. Azion goes in its MCP servers settings.AWSKiroAgentic IDE with a free tier and models from several providers. Azion goes in .kiro/settings/mcp.json.