Connect Your Assistant

This is the no-code path. Point an MCP-compatible AI assistant — Claude Desktop, Claude on the web, Cursor, or any other MCP client — at Divinci’s hosted server, sign in once in your browser, and the assistant can search your knowledge base, read and send chats, and operate on the rest of your account through the tool catalog.

You do not need the @divinci-ai/mcp package, an API key, or any code for this. (If you’re building your own agent in TypeScript, use the SDK client instead.)

Server URL

Divinci runs the MCP server at one endpoint per environment. Use production unless you’ve been told otherwise.

Environment	Streamable HTTP (preferred)	SSE (legacy)
Production	https://mcp.divinci.app/mcp	https://mcp.divinci.app/sse
Staging	https://mcp.stage.divinci.app/mcp	https://mcp.stage.divinci.app/sse
Dev	https://mcp.dev.divinci.app/mcp	https://mcp.dev.divinci.app/sse

Tip

The server speaks both the modern Streamable HTTP transport (/mcp) and the older SSE transport (/sse). Newer clients should use /mcp; use /sse only if your client doesn’t support Streamable HTTP yet.

Add the server to your client

Claude (web)

In Claude on the web, open Settings → Connectors → Add custom connector, then paste the server URL:

https://mcp.divinci.app/mcp

Claude registers itself automatically (Dynamic Client Registration) and opens a Divinci sign-in window. After you approve, the Divinci tools appear in the connectors menu.

Claude Desktop

Open Settings → Developer → Edit Config (or edit claude_desktop_config.json directly) and add:

{
  "mcpServers": {
    "divinci": {
      "url": "https://mcp.divinci.app/sse"
    }
  }
}

Restart Claude Desktop. On first use it opens a browser window for Divinci sign-in.

Note

Older Claude Desktop builds can’t reach a remote URL directly. If "url" isn’t recognized, use the mcp-remote bridge instead:

{
  "mcpServers": {
    "divinci": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.divinci.app/sse"]
    }
  }
}

Cursor

Add to your Cursor MCP settings (~/.cursor/mcp.json or Settings → MCP → Add new server):

{
  "mcpServers": {
    "divinci": {
      "url": "https://mcp.divinci.app/sse"
    }
  }
}

Cursor prompts you to sign in to Divinci the first time it connects.

Other clients

Any MCP client that supports a remote server over Streamable HTTP or SSE works. Give it the server URL and let it handle OAuth:

{
  "mcpServers": {
    "divinci": {
      "url": "https://mcp.divinci.app/mcp"
    }
  }
}

The server advertises OAuth metadata at /.well-known/oauth-protected-resource and /.well-known/oauth-authorization-server, supports Dynamic Client Registration at /register, and exposes an agent card at /.well-known/agent-card.json — so compliant clients discover and complete the sign-in flow with no manual configuration.

Sign in (the first connection)

1. Connect. Your client opens a Divinci sign-in window the first time it reaches the server.

2. Authorize. Sign in with your Divinci (Auth0) account and approve access. The assistant connects on behalf of your identity, so it can only see and change what your account is permitted to.

3. Use the tools. The assistant now lists Divinci tools and can call them. Try: “Search my Divinci knowledge base for refund policy” or “List my Divinci releases.”

There is no API key in the config — authentication is OAuth 2.0 (Auth0, PKCE). The browser flow runs on first connect and the client refreshes tokens silently after that.

Static API key (alternative)

If your client can’t do an interactive browser flow — a headless agent, a CI job — use a Bearer API key from the API Keys page of your Divinci workspace instead of OAuth:

{
  "mcpServers": {
    "divinci": {
      "url": "https://mcp.divinci.app/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_DIVINCI_API_KEY"
      }
    }
  }
}

The API key’s permissions scope exactly what the assistant can do — the same permission model as the OAuth identity.

Caution

Treat the API key like a password. It carries every permission granted to it; store it in your client’s secret store, never in a shared or committed config file.

What can the assistant do?

Everything your account is permitted to — knowledge-base search, chat, releases, RAG ingestion, fine-tuning, QA, analytics, notifications, and more. See the full list:

Tool Catalog Every tool an assistant can call, grouped by area.

Authentication The Auth0 PKCE flow in detail (for SDK builders).

Premium tools & payments Pay-per-call tools via x402.