An AI connected to Cobrain has seventeen tools: eleven to read and search, five to write and reorganise, one to delete. All of them work with your permissions: what you cannot do, it cannot do either.
A standard remote MCP server, with OAuth 2.1. One address, for every AI.
https://cobrain.space/mcpMCP over HTTP (Streamable HTTP). The program registers itself, the user authorises on a Cobrain page that states what the program will be able to do, and it receives a grant that expires and renews. No API key. Every tool runs with the identity of the user who authorised it: the same rules as the site, applied by the database.
Paste this message into the conversation: it carries the server name, the address and the kind of authentication. Many programs configure themselves; the others tell you where to add it.
Add the remote MCP server "cobrain" to your environment: https://cobrain.space/mcp Use OAuth authentication in the browser. If you cannot edit the configuration yourself, walk me through it step by step using the exact menu names.
If the program only accepts a command, the bridge is npx -y mcp-remote https://cobrain.space/mcp. If it asks for an API key, there is none: ask it for a remote MCP server over HTTP with OAuth.
Name, what it does, and whether it reads, writes or deletes. Errors reach the AI in English, suggesting the right path when it gets one wrong: your AI relays them to you in your own language.
list_workspacesYour brain and the ones shared with you, with the access you have on each. It also says which account the AI is connected as.
readslist_filesThe list of notes under a folder. If the folder does not exist, it suggests similar names.
readsfind_notesFinds notes and folders by name or by part of a path, like a computer's «find». It also resolves a [[wikilink]].
readssearchSearches the text of your brain and the shared ones. It returns whole lines containing the words, and tells the AI to read the note before answering.
readsread_fileReads a note.
readsload_contextEverything under a folder (or carrying a tag) in one go, instructions first: brain rules, the unit's index card, decisions, then the notes. It states when it had to truncate.
readsstart_sessionThe briefing for a unit (a client, a project…): rules, index card, instructions, decisions, open sub-units and the last fifteen changes.
readslist_unitsThe units in the brain: path, type, status, how many notes, last change.
readsrecent_changesRecently changed notes, by whom and when.
readsfiles_by_tagThe notes carrying a given tag.
readswrite_fileCreates a note, or replaces all of its content. It refuses to replace a long note with a much shorter text without confirmation: that guards against an addition mistakenly written as a rewrite.
writesappend_fileAdds text to the end of a note (creating it if missing). This is what the AI should use to add something, rather than rewriting.
writescreate_unitCreates a unit (a client, a project, whatever you follow) from a template: index card, AI instructions, decisions. On an existing folder it only adds the files that are missing.
writesmove_fileRenames or moves a note, or a whole folder.
writesdelete_fileDeletes a note, or a folder with everything inside it. The previous versions of the notes remain.
deletesstart_projectThe script for a guided brainstorm to set up a new unit with you: what to follow, what to call it, how to structure it. It changes nothing on its own.
guidesFor anyone assessing the connector before authorising it.
Every call is logged: which tool, with what outcome, in how long. And every note says which program changed it. For the rest, the privacy policy.
The guides walk you through Claude, ChatGPT, Claude Code, Codex and Antigravity step by step. For everything else, the message above.