MCP overview
What GuruSup Brain gives your AI assistant once you connect it, how the assistant is told to behave, and who can use it.
GuruSup Brain does not have a chat window of its own. You use it through your AI assistant, such as Claude, ChatGPT, Cursor or Codex. Brain connects to the assistant over MCP, a standard way for an assistant to use outside tools. The assistant asks Brain, Brain returns evidence from your organization's memory, and the assistant writes the answer. Brain does not write answers.
What your assistant can do with Brain
Once connected, your assistant gets 13 tools. The Tools reference lists every one. In plain terms, it can do the following.
| Ability | What it means |
|---|---|
| Ask | The assistant asks a question. Brain returns excerpts, the facts behind them, and the title and reference of the pages they come from. This is the main way to use Brain. See Ask questions. |
| Search | The assistant looks for pages that match a topic and gets a short list of hits. |
| Retrieve | The assistant opens specific pages found by asking or searching, when it needs more of the text. It asks for a few at a time. |
| Save knowledge | The assistant can send Brain a new fact you told it, such as a decision or a policy. It is meant to do this only after you ask or confirm. |
| Use skills | The assistant sees the skills you have access to and loads one when it needs it. When you ask, it can also submit a skill you wrote. A submitted skill is not usable until an admin approves it. See Skills. |
| Ask a person | When Brain has no answer, the assistant can offer to ask a colleague who is set up as a contact. It shows you who first and sends the request after you confirm. If you ask to be contacted yourself, that request counts as the confirmation. See Contacts and My requests. |
| Report a problem or send feedback | The assistant can report a failure it can point to, and suggest an improvement when nothing failed. Neither changes what Brain knows. |
Four things change something outside the conversation: saving knowledge, submitting a skill, asking a person, and sending a report or feedback. Reports and feedback only record a note for the GuruSup team, but they still leave the conversation. No tool edits or deletes knowledge that is already saved.
How the assistant is told to behave
Connecting a server gives the assistant tools. What it does with them comes from two places: Brain's own instructions, which it receives when it calls init, and the short instruction you save in your assistant (see Setup).
The instruction you save only says to use Brain for company questions and to call init first. The detailed rules arrive with init, so they always match the current version of Brain. In summary, the assistant is told to:
- Call
initonce per task or session, before the first read, and treat the result as the rules to follow. - Ask Brain first with
ask_company_memory. Use search and retrieve only as a fallback. - Answer only from what Brain returns, and cite the titles and links Brain returned.
- Keep scores, rankings, confidence, gaps and other internal signals out of the answer, unless you ask for search diagnostics.
- Say what Brain's evidence supports and what it does not, instead of guessing. Not seeing a fact in the excerpts does not prove Brain does not have it, so the assistant says the returned evidence does not establish it.
- Say a short equivalent of "I could not find anything" when nothing comes back, in your language.
- Not present a service, sign-in or connection error as an empty result. It should explain the problem plainly, without backend details.
- Offer to ask a colleague only when a fact stays unsupported, and only a contact that Brain returns after a preview. If no contact is available, it says so and does not suggest a person.
- Report a failure once it is confirmed, and send feedback once at the end of a task.
The instruction is a request to the assistant, not a lock. A different model or client can follow it less closely. If an assistant does not use Brain, see Troubleshooting.
Your assistant only uses Brain if it has been told to. Adding the server is not enough. The prompt on the Brain MCP page saves that instruction for you, and each client page shows where to paste it by hand. See Setup.
What costs usage
Asking is not metered. Questions, searches and lookups do not use up your plan's usage. Content that Brain reads does, and that includes knowledge an assistant saves. When usage runs out, Brain keeps answering and new content waits for the next period. Saved knowledge is new content, so it waits too. See Plan and usage.
If ingestion is paused for your organization, saved knowledge does not become available while the pause lasts. When Brain accepts a saved note, the assistant tells you "Listo." and that the information will be available in a few minutes. That confirmation means Brain accepted the note. It does not mean the note is searchable yet.
Knowledge saved through an assistant cannot be edited or removed from the app afterwards.
Who can use it
Any member of the organization can connect an assistant and use Brain through it. You do not need to be an admin. The Brain MCP page is in the sidebar for everyone.
Brain answers only once an admin has built the organization's memory. Until then, the tools tell the assistant that Brain is not ready. Members cannot build the memory. See Troubleshooting.
Each person signs in to Brain from their own assistant, and one connection is one person in one organization. What the assistant can see depends on who signed in, not on which assistant it is. See What an agent can see.
How sign-in works
The first time your assistant connects, it may open a browser window so you can sign in to GuruSup Brain. After that, the assistant uses that sign-in. You do not paste a password or a key into the assistant. If you belong to more than one organization, you choose the organization when you sign in.
Approval prompts in your client
Each Brain tool is marked as read-only or not, and as destructive or not. Your client can use those marks to decide when to ask you before running a tool. Whether it asks, and how, is the client's choice, so the same tool can prompt you in one client and not in another. The Tools reference shows the marks.
What you get back
Brain returns evidence, and the assistant decides how to word the answer. A citation names a page of Brain's memory, not the original document. See Sources and citations.
Next step
Connect your assistant with Setup and authentication.