> For the complete documentation index, see [llms.txt](https://docs.kula.digital/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.kula.digital/for-developers/overview.md).

# Overview

Kula Intelligence is a **remote** [**MCP**](https://modelcontextprotocol.io) **server**. AI clients connect to it, authenticate, and call a curated set of tools that read and (where permitted) write a single studio's operational data.

This section is for developers and integrators — agencies building on the Claude API, technical staff wiring up Claude Code, or anyone who wants the detail under the owner-facing guides.

## The shape

* **No anonymous access.** Every connection carries a **role-scoped credential created in console.kula.digital** — a **connect link** (`/connect/{…}/mcp`, OAuth) for Claude, or an **access token** (bearer) for other clients. Served over **streamable HTTP**.
* **One studio per connect link.** Every request is authenticated, and the credential identifies exactly one studio. Tenancy is enforced by a **database boundary** — each studio's data lives in its own Postgres database, and there is no cross-studio read path. The studio is derived from the credential, never from a tool argument.
* **A curated tool surface, not raw database access.** Clients don't run arbitrary SQL against the engine. They call purpose-built tools (`list_tables`, `execute_query` for read-only SELECTs, `entity_lookup`, `get_member_plan_status`, and so on). Reads are scope-gated; writes go only through guarded, audited tools. See the [tool reference](/for-developers/tools.md).
* **Skills as prompts.** The skill library is surfaced as **MCP prompts**, so curated playbooks work in any compliant client.

## Authentication, in one line

There is no open, anonymous access — every client connects with a **role-scoped credential created in console.kula.digital**, and which kind depends on the client:

* **Connect link (OAuth)** for clients with a custom-connector flow (Claude): `https://mcp.kula.digital/connect/{…}/mcp`; using it runs the OAuth handshake (discovery, registration, PKCE, sign-in, consent — see [OAuth](/for-developers/oauth.md)).
* **Access token (bearer)** for other clients: minted in console.kula.digital and presented as `Authorization: Bearer <token>` against `https://mcp.kula.digital/mcp`. See [Connect](/for-developers/connect.md).

Either way the credential carries its [permission level](/connect-claude-and-access/scopes.md); the runtime verifies it, derives the studio and level, and routes to that studio's database.

## What it deliberately doesn't do

* No money movement, refunds, or transfers.
* No AI media generation.
* No cross-studio reads — not even for analytics.
* No arbitrary DML/DDL. `execute_query` is SELECT/`WITH`-only; mutations go through specific, audited tools.

## Where to go next

* [Connect — API, Code, Cursor, Lovable](/for-developers/connect.md) — wire up a client.
* [Tool reference](/for-developers/tools.md) — every tool, with read-only/destructive flags.
* [Schema reference](/for-developers/schema.md) — the tables and columns behind the freeform query tools.
* [OAuth](/for-developers/oauth.md) — discovery, DCR, PKCE, scopes, audience binding.
* [Changelog & versioning](/for-developers/changelog.md) — how the surface evolves.