Skip to main content

MCP

Create a connection token

What connecting an outside AI assistant to Nirvai gives you, and how to create the private token it uses to act in your account.

Think of Nirvai as a pair of hands your favourite AI assistant doesn't have yet. You already chat with a coding or writing assistant — Claude Code, Codex, Cursor, Gemini — and it's great at thinking. What it can't do is remember across chats, keep your data in one place, run your real tools, or build something that outlives the conversation. One connection gives your assistant all of that: it can use everything in your Nirvai account.

Two directions, one standard

This section is about an outside assistant using your Nirvai account.

The reverse — your Nirvai agent using an outside app like Linear or HubSpot — is MCP servers, on the Integrations page.

TermWhat it is
Your assistantThe outside AI tool you already use (Claude Code, Codex, Cursor, Gemini…). It keeps doing the thinking.
Connection tokenA private code that lets your assistant act in your Nirvai account, and nothing else.
MCPThe "Model Context Protocol" — a shared plug every modern AI assistant understands, so the same connection works with any of them.

How it works​

Your assistant keeps doing the thinking. Nirvai does the doing and the remembering — every action runs safely in your Nirvai account, never on your assistant's side.

Shared projects

The same projects your Nirvai agents use — so facts learned in one place are known everywhere.

Your real tools & data

Databases, hundreds of pre-built connections, and your own tools — reused, never re-pasted.

Agents & live apps

Build, run and edit Nirvai agents and interactive dashboards straight from your assistant.

Create your token​

A connection token is like a key card for a trusted colleague: it opens your Nirvai account, within the permissions you choose. You create it once in Settings → Connections:

1Mint a tokenShown once — right after you create it.
Token name
e.g. My Claude Code
Provider
Claude CodeAnthropic's terminal agent. Add Nirvai with claude mcp add.
Tags every run in the feed so you know which agent did what.
ScopesFull access recommended
read
list & describe your resources
run
execute tools, agents & searches
write
edit existing resources
create
create new resources
read + run need no confirmation. write + create let the agent change and build things.
Create token
  • Name — so you recognise it later.
  • Provider — your assistant. This tags every action in the Activity Feed.
  • Scopes — what it may do. Full access is recommended; read + run never need confirmation, while write + create let your assistant change and build things.

Copy the token now — it's shown once.

Treat it like a password

Anyone with the token can act in your account within the scopes you gave it. Don't paste it into a public chat or commit it to a repo. Lost or shared it? Revoke it on the same page and mint a new one.

What's next​