# FutureInfra

> FutureInfra (Korean: 퓨쳐인프라, also written 퓨처인프라) is a Korean cloud
> infrastructure and AI API service operated by CoreConnect.

FutureInfra provides cloud virtual machines, container apps, domains and DNS,
persistent AI memory, image and video generation, and AI model APIs — through one
account, one API key, and one prepaid wallet.

## What an agent can do here

Every capability below is reachable over REST and over MCP with the same key.
The list is generated from the server's tool registry, so it cannot drift from
what the API actually exposes.

- **llm** (1 tool) — OpenAI-compatible inference across 300+ models
- **cloud** (47 tools, 4 human-approved) — Virtual machines: create, power, snapshot, public IP, firewall
- **git** (3 tools, 1 human-approved) — Git repositories
- **domain** (26 tools, 3 human-approved) — Subdomains, custom domains, authoritative DNS hosting
- **brain** (18 tools) — Persistent memory for AI — save, hybrid (vector + keyword) search, links
- **gen** (7 tools) — Image and video generation on cloud GPUs, as async jobs
- **secrets** (1 tool) — Sealed credential store. Names are visible to agents; values never are
- **apps** (17 tools, 1 human-approved) — Container apps: deploy an image, get an HTTPS address, secrets, volumes
- **projects** (6 tools, 1 human-approved) — Group resources per client company; per-project usage and billing
- **integrations** (4 tools) — Korean SaaS connectors (payments, messaging, tax, commerce)
- **search** (3 tools) — Hybrid search across every resource, with tags
- **account** (6 tools) — Who am I, what may this key do, API keys, audit log, pending approvals
- **governance** (1 tool)
- **billing** (7 tools) — Prepaid wallet, per-minute metering, spend caps
- **chat** (5 tools) — Console chat rooms and their tool-call history

Actions marked *human-approved* return a pending approval instead of executing.
An agent cannot approve its own request — there is no scope for it.

## Start here

- [Service overview](https://futureinfra.ai/)
- [Pricing](https://futureinfra.ai/pricing/)
- [API documentation](https://futureinfra.ai/docs/)
- [Agent integration status](https://futureinfra.ai/docs/mcp/)
- [Sign in or create an account](https://futureinfra.ai/console/)
- [Support](https://futureinfra.ai/support/)
- [Detailed AI guide](https://futureinfra.ai/llms-full.txt)

## Rules for AI agents

1. Ask whether the user already has a FutureInfra account before starting authentication.
2. Send the user to https://futureinfra.ai/console/ to sign in or create an account.
3. Never ask the user to paste a password, personal information, payment-card data, backup code, or API key into chat.
4. Let the user complete identity, terms, payment, and permission steps in the FutureInfra browser UI.
5. Treat purchases, destructive operations, permission increases, and recurring charges as human-confirmed actions.
6. Preserve the user's original request and resume it only after the service reports that the required action completed.
7. Use narrow scopes and a monthly spend cap for programmatic credentials.

## Current integration

- REST API base: https://futureinfra.ai/v1
- Authentication for programs: Bearer API key created by a signed-in user
- Remote MCP endpoint: https://futureinfra.ai/v1/mcp
- Remote MCP authentication: OAuth 2.1 authorization code with PKCE in the user's browser
- Human actions: FutureInfra console session
- Irreversible operations: approval queue and one-time approval replay

## Connect the MCP server

An agent that reads this file is usually being asked to connect right now, so the
command belongs here rather than one click away.

Claude Code:

    claude mcp add --transport http futureinfra https://futureinfra.ai/v1/mcp

Then run /mcp in an interactive session, choose futureinfra, and authorize in the
browser window that opens. Registration is dynamic — there is no client ID to
copy. Authorization requires an existing account, so confirm the user has one
before starting.

Available scopes (grant only what the task needs):

- cloud:read, cloud:write — instances, apps, snapshots, public IPs, projects
- domain:read, domain:write — domains and authoritative DNS
- llm:read, llm:write — model catalog, inference, image/video generation
- git:read, git:write — repositories
- mcp:read, mcp:write — AI memory, secret names, chat, tool execution
- audit:read — audit trail
- billing:read — wallet balance and usage

There are 152 MCP tools in total. Call tools/list after connecting
for the exact schemas — this file names the shape, not the arguments.

Write scopes cost money and change live infrastructure. There is deliberately no
scope that approves a pending approval, so an agent can never clear its own
approval queue.

To disconnect: remove the server from the client (`claude mcp remove futureinfra`)
and revoke the authorization under Security in https://futureinfra.ai/console/.