Hands in your apps.
Gmail, Slack, GitHub, Notion and hundreds more, with permission.
Apps work in our code today. We are checking them on customer keys before this says Live.
What your agent can do with it
- Draft a reply in Gmail for a user to approve.
- Post an update to a Slack channel when a job finishes.
- Open a GitHub issue from a bug report.
- Add a row to a Notion database.
How it reaches your agent
Each user connects their own accountsShipping
They sign in to each app with OAuth. Your agent can only act where that user has said yes.
One MCP server for every appShipping
Your agent searches for the action it needs, then runs it.
Works with Murage, Wayland, Claude Code, Codex, Cursor, Hermes, OpenClaw, Cline, and anything else with an OpenAI or Anthropic endpoint. See the setup guides.
Price
- App actionsPriced per call.
Limits
- Each user connects their own accounts, with OAuth.
Why not wire it up yourself?
One account instead of several
No separate sign-up, key and billing page for each provider behind an ability.
One key, one bill
Every ability is billed to your Flux account, on one bill.
Nothing new to maintain
No extra SDKs to study or keep current. Your agent talks to one endpoint it already knows.
Questions
Whose accounts does my agent use?
Each user’s own, connected with OAuth. Your agent acts only where that user has said yes.
Is it live?
It is shipping. This page will say Live once apps are checked on customer keys.
One key. Everything behind it.
Your agent keeps its brain. Flux gives it the rest, on one key and one bill.