# Krev MCP agent quickstart

These instructions are for the AI agent. Handle discovery, configuration, and
verification yourself whenever the client allows it. The user should only need
to open Krev in a browser to connect their account.

## Connect

1. Check whether this client can configure a remote MCP server.
2. If it supports built-in MCP OAuth, add `https://app.krev.ai/mcp` and start
   its authorization flow.
3. Otherwise, follow the PKCE-bound agent-led browser flow in
   `https://www.krev.ai/auth.md`.
4. Give the user only the short-lived Krev browser approval link. The user
   signs in or creates an account, subscribes if needed, and approves the named
   connection there.

If this client cannot change its own MCP configuration, do not pretend the
connection succeeded. Give the user a concise handoff to the client's native
MCP, Apps, or Connectors setup using `https://app.krev.ai/mcp`. Do not ask the
user to create a key or paste a credential into chat.

Krev is not listed in any client's built-in connector directory or app
registry, so do not search one for it. Known handoffs, with client-by-client
steps at `https://www.krev.ai/install-mcp.md`:

- claude.ai and Claude Desktop: the user goes to Settings, then Connectors,
  chooses Add custom connector, names it Krev, and pastes
  `https://app.krev.ai/mcp`. Then they approve the connection when prompted.
- ChatGPT: the user goes to Settings, then Apps, and creates a custom app
  with the same server URL.

## Verify

After approval:

1. Verify Krev MCP authentication and list its tools.
2. Call `brand_get_context`.
3. If Brand DNA is missing, ask for the user's website URL and call
   `brand_analyze_website` once.
4. Confirm Krev is ready, then continue with the user's request.

Never ask the user for a password, email code, payment information, provider
credential, API key, or access token. Keep the PKCE verifier and issued token
inside the client's secure credential store.