Install the connection

You've minted a token — now hand it to your assistant. It's one command: your Nirvai address (already filled in below) plus the token you copied.

Run the command for your assistant

Replace <YOUR_TOKEN> with the connection token from Settings → Connections.

Your Nirvai connection addresshttps://3kt55hmm4ixi5duur67snxkgz40nklgn.lambda-url.us-west-2.on.aws/nirvai/mcp

Claude Code

claude mcp add --transport http nirvai "https://3kt55hmm4ixi5duur67snxkgz40nklgn.lambda-url.us-west-2.on.aws/nirvai/mcp" --header "Authorization: Bearer <YOUR_TOKEN>"

Any MCP client

npx add-mcp "https://3kt55hmm4ixi5duur67snxkgz40nklgn.lambda-url.us-west-2.on.aws/nirvai/mcp" --header "Authorization: Bearer <YOUR_TOKEN>"

Replace <YOUR_TOKEN> with the connection token you copied.

That's it — your assistant now sees Nirvai. Ask it "What do I have in Nirvai?" and it will list your agents, databases and connections. The first thing it usually offers is to reconcile what it already knows about you into your shared project.

Try a slash command

In your assistant's prompt, type /nirvai: to see Nirvai's built-in commands — connect, remember, recall, new_agent, activity and more. They're shortcuts that kick off the right steps for you.

Teach it what Nirvai can do

Your assistant can now reach Nirvai, but a fresh chat doesn't know when to use each capability — a database, a project, an automation. Drop one starter file into your project and it learns them all. Pick your assistant, download the file (or copy it in), and edit it however you like.

Rendered for

Starter set

your-project / CLAUDE.md

CLAUDE.md

Nirvai instructions your agent reads every session

When it loads

Loaded into context at the start of every Claude Code session.

Tells the agent that Nirvai is connected and — the part a fresh session is missing — when to reach for each capability. Copy it in and edit it freely.

Working with Nirvai (connected over MCP)

Nirvai is your backend and native UI: shared memory, structured databases, hundreds

of credentialed tools, cloud skills, agents, live apps, and automations — with an

activity feed where every action you take is visible and deep-linked.

The shape of every action

• Discover, don't guess: nirvai_list_resources(kind) then nirvai_describe(ref). Address resources by their uuid, never by name.
• One thing per call: nirvai_execute(alias, args, description, session). description is a REQUIRED one-line "why" — it is what the user reads in their feed.
• Keep a session: nirvai_create_session(name) once, pass its uuid as session on every related call so the work threads together.
• Every call returns a link. Hand it to the user; never paste raw data dumps.

First move in a new session

1. nirvai_download_skill_package("_root", session) and read it.
2. nirvai_list_resources for what already exists — reuse by uuid before creating.
3. nirvai_describe the thing you will touch, download its entity pack, then act.

Where each kind of data belongs

• Databases — anything that is a LIST OF RECORDS THAT NEEDS ORDER: a CRM of contacts, a task tracker, leads, inventory, invoices. Spaces hold Databases (tables) with typed columns (text, status, select, date, person, relation, file) and views (grid, kanban, calendar, form). Verbs: db.create_space, db.create_database, db.create_view, db.insert, db.update, db.select. Hand back the table link.
• Projects — long-term KNOWLEDGE ABOUT SPECIFIC THINGS you must remember across conversations: a client's preferences, an ongoing investigation, decisions and their reasons. A knowledge graph plus a file appendix. Verbs: projects.recall, projects.add, projects.store_file. Reach for a Project when the fact matters next week, not just this turn — and projects.recall BEFORE you answer from memory.
• Live apps — an interactive dashboard or app built on the user's real tools and data, not a static report. Verbs under live_apps.*.
• Agents — build and run AI agents on the user's account: agents.run, agents.create. Delegate a real task, then show the run transcript link.
• Automations — a workflow on a trigger (manual, schedule, webhook, or an app event) with agent steps and free deterministic steps. Flow: automations.templates then automations.validate(spec) then automations.create(spec); hand off the review link — the user tests and activates.
• Tools & credentials — connect a provider and run its credentialed tools in the cloud. Call credentials.native_requirements and tools.search_templates FIRST, then tools.use. Built-ins: web.search, web.fetch, media.image.
• Skills — run one of the user's cloud skills end to end: skills.run.
• Help — docs.search / docs.read for product documentation.

Non-negotiables

• You NEVER hold a secret. Propose a credential by field NAME; the user types the value on the link Nirvai returns. Never ask the user to paste an API key into chat.
• Reuse before you create. A retry with the same idempotency_key will not duplicate.
• One plain-language description per action. It is the spine of the activity feed.

Master tools

nirvai_list_resources · nirvai_describe · nirvai_execute · nirvai_create_session ·

nirvai_list_sessions · nirvai_get_session · nirvai_sync_session · nirvai_transfer_file ·

nirvai_download_skill_package

Recipes

Stand up a CRM

1. db.create_space { name: "Sales" }
2. db.create_database { database_session, name: "Contacts", columns: [...] }
3. db.insert / db.select — hand back the table link.

Remember a client across sessions

1. projects.create_store { name, description } (description = when to use it)
2. projects.add to store observations; projects.recall next time before answering.

Run a task with an agent

1. nirvai_list_resources("agents") then pick by uuid
2. agents.run { agent_uuid, message } then show the run link.

Ship an automation

1. automations.templates then pick a trigger
2. automations.validate(spec) then fix the reported issues
3. automations.create(spec) then send the review link; the user tests + activates.

Or let the assistant write it

Already connected? Just run /nirvai:setup_file and your assistant writes this file into your project for you.

Troubleshooting

Problem	Fix
The command shows the address as <your-nirvai-backend>	The connection address wasn't set for this docs build. Grab the exact address from Settings → Connections in the app — it's shown next to the install snippet there.
"Unauthorized" / the assistant can't see anything	The token is wrong, expired, or was revoked. Mint a fresh one in Settings → Connections and re-run the command.
It can read but can't create	The token's scopes are too narrow. Mint a new token with write and create enabled.
A review page asks for a password	That's expected — secrets are always entered by you, on Nirvai's secure page. Your assistant can't complete a login for you.

What's next

Keep going

See what your agent does in the Activity Feed, or read the MCP documentation for the full picture of what the connection exposes.