Skip to main content

Agents & connected apps

You can connect AI agents and other tools to your DFOS account, so they can work in your spaces on your behalf. This is open to everyone — no waitlist, no approval. A connected agent acts as you, so the whole model rests on connecting only tools you trust.

There are two ways something outside DFOS can reach your account, and they are not equally powerful.

A connected agent — an AI assistant you connect over MCP — acts as you and sees everything you see. That is the powerful one, and the whole of its safety is in who you connect.

Signing in to another app with DFOS is narrower: that app gets only what you explicitly grant on the consent screen, and nothing else. That screen is the authoritative list — it names every single thing the app asked for, one line each, so read it rather than assuming. Some lines are facts about you: your public identity, your profile, your email address, the spaces and groups you belong to. Others let the app act as you inside spaces you name — read the posts and comments you can see there, upvote, or write, edit, and delete your own posts and comments. This is also how a command-line tool or a desktop app asks for access, so a tool on your own machine can hold a narrow grant rather than your whole account.

Connecting an AI agent​

DFOS speaks the Model Context Protocol, so agents like Claude can work with your spaces directly. In Settings → MCP you'll find your connection URL — copy it and paste it into your agent's connector settings.

When the agent first connects, DFOS shows you an Authorize Application screen with the account it's connecting as, and nothing is connected until you choose Authorize. The agent signs in as you the same way you do — there's no password to hand over and no separate key to manage.

What a connected agent can do​

A connected agent works as you: it can do the everyday things you can do in your spaces, and it can't do anything you couldn't. In broad strokes, that means it can:

  • Read what you can read — your spaces, posts, chat and direct messages, notifications, and members, all scoped to what you already have access to.
  • Post and comment in the spaces you're in, and attach media.
  • Edit and delete your own posts and comments, and delete your own messages.
  • Send messages in space chat, direct messages, and group DMs, and start, add people to, or leave a group DM.
  • Search across your spaces for people, posts, and conversations.
  • Join and leave spaces and groups, and apply to spaces that take applications.
  • Take everyday actions — follow someone, react, upvote, bookmark, and the like.
  • Change group roles where you hold that authority, the same as you could in the app.
  • Read these docs, so it can look up how something on DFOS works before it acts.

The consent screen states the one hard limit plainly: "It can't make purchases or move money."

Everything else is your account in an agent's hands. It sees what you see — including your private messages — and acts under your name, so treat connecting an agent like handing someone your keys. It can remove things as well as add them.

Ending an agent connection​

An agent connection doesn't appear under Settings → Connected apps; that list holds sign-in grants. To end an agent's access, disconnect from the agent's side: remove the DFOS connector in the agent's own settings.

Tools and scripts of your own​

A tool you run yourself — a command-line tool, an agent you wrote, a desktop app — has the same two doors everyone else does, plus a third that skips DFOS entirely.

  • Connect it over MCP if it should work in your spaces on your behalf, the way an assistant does. Same connection URL, same consent screen, same "acts as you" reach.
  • Have it sign in with DFOS if it needs something specific rather than your whole account. It gets a standing grant covering exactly the lines you approved — and, where those lines reach into spaces, only the spaces you named on the screen. It appears under Settings → Connected apps as Local application, and is revocable there like anything else. That is the narrow door, and it is the right one for most tools. The developer side is Local applications.
  • Point it at the protocol if it should not touch DFOS at all. Your identity is a signed chain published to a public relay; a tool holding a key you control can verify and publish against that directly, with nothing issued here and nothing here to revoke. See Sessions, grants, and keys.

Signing in to another app​

Other apps can offer a "Sign in with DFOS" button. Approving one is a different thing from connecting an agent: the app gets what the consent screen says and no more. The screen lists every line the app asked for, written by DFOS rather than by the app, and where a line reaches into spaces it also says which ones. The full set of lines, with what each covers, is in Scopes and credentials.

The screen leads with who is asking: an app's domain on the web, or Local application for a tool on your own machine. What DFOS can and can't confirm about a local tool is in Local applications. Either way, approve only a screen you arrived at by starting a sign-in yourself.

A grant stays valid until it's revoked. Settings → Connected apps lists every app you've signed in to and what each can do; disconnect one there, or all of them at once, and it takes effect on that app's next request. Deleting your DFOS account ends every grant with it. Revoking ends an app's access but doesn't un-share what it already read, so share your email address only with apps you're willing to give it to. What that list does and doesn't cover is in Sessions, grants, and keys.

If you're building an app that uses this, see Sign in with DFOS.

Staying in control​

A few habits keep agent access safe and predictable:

  • Connect tools you trust, and understand their scope. An agent acts as you and can reach everything you can, private messages included. Only connect software you'd trust with that.
  • Give clear intent. An agent does what you ask, so be specific about what you want it to do — and, especially early on, review what it posts, sends, or removes before it acts.
  • Only approve prompts you started. Approve a connection or a sign-in when you're the one who kicked it off. If a consent or device-approval screen appears and you didn't initiate it, don't approve it.
  • Check your grants now and then. Settings → Connected apps is the full inventory of standing sign-in grants, including any local applications. Disconnect anything you don't recognize. For agents, check the connectors in each agent you use.