What it is
If you already pay for an AI assistant (Claude, ChatGPT or another), you can connect it to ōrbita and ask for things in its own chat: “rewrite the copy of Thursday’s post in a warmer tone”, “prepare three drafts for the autumn campaign”, “explain this month’s metrics”. Your assistant reads what ōrbita knows about your company (strategy, brand voice, catalogue, reviews, calendar, metrics) and writes the result straight into ōrbita.
The connection uses MCP, the standard AI assistants use to connect to other applications. There are no keys to copy and nothing to install: you paste an address, sign in to your ōrbita account and authorize.
The connector address is always the same:
https://mcp.orbitasolutions.org/mcp
You will also find it, with a copy button, in Connections, under Connected AIs.
What your AI can and cannot do
Your AI acts with your identity and your own permissions: it can never do more than you can do in each company. If you have Read level in a company, your AI only reads; if you are Editor or Admin, it can do what you can.
When you connect, ōrbita shows you a screen with what your AI will be able to do:
- Read: your companies and their context, the catalogue, social proof, posts and the calendar, key dates, the metrics of what has been published and the requests you leave for it.
- Optional permissions, each with its own checkbox: create drafts and edit posts, edit the communication plan, mark your requests as done, manage the catalogue, social proof and key dates, and read and reply to marketplace reviews. They come ticked; untick whatever you do not want to allow.
What it can never do, whatever permissions it has:
- Publish or schedule on your networks. It can leave a post with a date and time, but scheduling and publishing it is decided by a person in ōrbita.
- Tick for you the declarations each network requires to be made by hand (for example, branded content on TikTok or “made for kids” on YouTube).
- Upload images or videos. Your AI writes; you add the media in the post.
- See your billing or manage the members of your companies.
What your AI creates arrives as a draft, and you find it where you always do: without a date, in Drafts; with a date, in the Calendar. Your AI gives you the direct link to every post it touches.
The full list of what the connector offers your assistant, tool by tool, is in the tool reference.
Connect Claude
It works on every Claude plan. On the free plan, Claude allows a single custom connector.
- In Claude (web or desktop app) open Customize > Connectors, press + and choose Add custom connector.
- Give it a name (for example, ōrbita), paste the connector address and press Add. If Claude asks how to sign in, leave the default options.
- ōrbita opens: sign in to your account if you were not already, review the permissions and press Authorize.
- In a chat, press + > Connectors and turn ōrbita on. Try: “list my ōrbita companies”.
Once connected on the web or desktop, the connector also appears in the Claude mobile app. From Customize > Connectors you can decide, tool by tool, whether Claude acts without asking or asks for permission every time; for the ones that write, we recommend that it asks.
If you use Claude on a Team or Enterprise plan, whoever administers the organisation has to add the connector first; then each person connects it with their own ōrbita account. The official steps are in the Claude documentation.
Connect ChatGPT
In ChatGPT, custom connectors live in developer mode, a beta feature from OpenAI that is only available on the web. The exact menu path changes often: follow the official OpenAI article, paste the connector address when asked and authorize in ōrbita just as with Claude.
There is a limit set by OpenAI, not by ōrbita: on personal ChatGPT plans, a custom connector can only read. It is useful for checking your strategy, your posts or your metrics, but not for leaving drafts. Writing in developer mode is reserved for the Business, Enterprise and Edu plans. If you want your AI to write in ōrbita, today the way is Claude.
One detail: ChatGPT stores the connector’s list of functions as it was on the day you added it. When ōrbita adds new functions, delete the connector in ChatGPT and create it again to see them.
Connect Claude Code and Cursor
Claude Code. In the terminal:
claude mcp add --transport http orbita https://mcp.orbitasolutions.org/mcp
Then, inside Claude Code, type /mcp, choose ōrbita and follow the sign-in that opens in the browser.
Cursor. Add the server in ~/.cursor/mcp.json (for all your projects) or in .cursor/mcp.json inside a project:
{ "mcpServers": { "orbita": { "url": "https://mcp.orbitasolutions.org/mcp" } } }
Cursor opens the ōrbita sign-in the first time it uses the server.
Any other client compatible with MCP over HTTP and OAuth sign-in connects the same way: all it needs is the address.
Requests: asking for work from ōrbita
Besides asking for things in its chat, you can leave work prepared for it from ōrbita with Ask my AI:
- From a post: you say what you want (for example, “write the copy in the usual tone”) and the request stays linked to that post.
- From a calendar day: ōrbita creates an empty post for that day and the request for your AI to write it.
You can ask your own AI or that of another person in the company; the request is picked up by that person’s AI, with their permissions. Requests appear in Tasks with the “For your AI” label.
Important: ōrbita does not notify your AI. Assistants work the other way round: they are the ones who ask. Your AI picks up requests when you tell it to or when it has a scheduled task that does it on its own. Ask for the whole thing: “check whether I have pending requests in ōrbita, do them and mark them as done”. If you do not say so, some assistants do the work and leave the request open. When it closes one, your AI leaves a note with what it did.
Scheduled task: picking up requests on its own
If your assistant has scheduled tasks, you can have it check your requests every day without being asked. In Claude they live in Cowork, on paid plans: in the sidebar, Scheduled > New task, choose the frequency and write the standing instruction. A text that works:
Check my pending requests in ōrbita across all my companies. For each one, read the request and the company context, do what it asks on the linked post and mark it as done with a short note of what you changed. Do not touch anything that is not in a request. At the end give me a summary with the link to each post.
The official steps are in Claude’s help. Everything the task does reaches ōrbita as a draft: you still review before publishing.
Control and withdraw access
In Connections > Connected AIs you see every AI you have connected, when you connected it, when it was last used and which permissions it has. From there you can:
- Remove a specific permission without disconnecting it.
- Disconnect the AI altogether. What it had already created in ōrbita is left untouched.
Removing the connector inside Claude or ChatGPT does not withdraw access in ōrbita: always do it from Connections. And every time you add the connector in your assistant a new connection is created; the ones that stop being used are removed on their own after a while.
If you manage a company with more people, in the same section you see which people have an AI working in that company and you can block someone’s AIs in that company without touching their access to ōrbita. The block is per person: connecting the AI again does not lift it.
If something does not work
- Your AI says it has no permission for something. Either you do not have that level in that company, or you unticked that checkbox when connecting. To change the checkboxes, connect the connector again from your assistant.
- Your AI does not see a company. Check that you have access to it in ōrbita and that nobody has blocked your AIs in that company.
- It says it has reached the usage limit. The connector has a limit of requests per minute and per hour to protect the service. Wait a little and try again.
- It cannot edit a post. Posts that are already scheduled or published are locked for your AI just as they are for you in the app.
- The authorization fails or expires. Start the connection again from your assistant and complete the authorization without switching browsers.
Privacy
ōrbita does not see your Claude or ChatGPT account, your conversations or your subscription. What it keeps is which AI you have authorized, with which permissions, and a log of which operation it ran, in which company and when, without the content of the conversation. What your AI reads from ōrbita goes to your assistant’s provider under the terms you have with it. More in the privacy policy.
Who it is for
Included in every plan, at no extra cost, for all the companies in the account. You bring the AI: the connector works with the subscription you already have with your assistant.