> ## Documentation Index
> Fetch the complete documentation index at: https://developers.sapot.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Roadmap & Reserved Scopes

> What's coming next for the Sapot MCP surface, which scopes are reserved placeholders, and which actions still live in the dashboard.

<Note>
  The AI-native / MCP surface is verified on staging and rolling toward production. The tool catalog and the scope allowlist keep growing — this page tracks what's live, what's reserved, and what's still dashboard-only.
</Note>

Sapot Chat ships the agent surface deliberately: a capability is only reachable once its tools *and* its server-side guardrails are in place. Scopes that don't have live tools yet are **reserved** — you can see them, but they refuse until their tools land. Everything below is forward-looking.

## Reserved scopes

The scope catalog is intentionally larger than the live tool set. One scope is a reserved placeholder today:

| Scope               | Status                   | Behavior today                                                                                                        |
| ------------------- | ------------------------ | --------------------------------------------------------------------------------------------------------------------- |
| `automation:manage` | Reserved (no live tools) | In the catalog, so you *can* grant it — but no endpoint maps to it yet, so any automation call is **default-denied**. |

Because enforcement is a **default-deny allowlist**, a reserved scope grants nothing on its own. If a key carries `automation:manage` and tries to reach an unmapped endpoint, the server refuses with `This endpoint is not available to agent access tokens` — not a scope error, because no tool is wired up behind it. Granting it early has no effect and is safe; it simply lights up when automation tools ship.

<Tip>
  The `*` (full) scope is not a bypass. It satisfies the scope check for every mapped endpoint, but it still can only reach endpoints that have live tools — reserved capabilities stay dark for `*` too.
</Tip>

## What still lives in the dashboard

These actions are **out of scope for an agent by design**, not missing features. A human does them in the app.

<CardGroup cols={2}>
  <Card title="Sending a blast" icon="paper-plane">
    Agents <b>draft</b> campaigns and preview audience; the send stays a human dashboard click. There is no autonomous-send scope.
  </Card>

  <Card title="Building a flow" icon="diagram-project">
    There is no create-from-intent, export, or import tool over MCP. Design flow agents in the Flow Designer; the agent operates and publishes them.
  </Card>

  <Card title="Channel & inbox setup" icon="robot">
    Connecting a WhatsApp / Facebook / Instagram channel (OAuth) and creating inboxes is UI-only — no MCP tools for it.
  </Card>

  <Card title="AI knowledge generation" icon="sparkles">
    Generate-from-text/file, bulk operations, and document import are omitted (LLM cost + blast radius). Agents do plain CRUD + approve.
  </Card>
</CardGroup>

The campaign and flow boundaries are permanent product decisions — see the Campaigns and Flow Agents pages for how to work within them. The knowledge, channel, and setup gaps are candidates for future tools.

## Deferred controls

<Warning>
  There is **no per-minute, per-token rate limit** yet. Today, the only cap is the **per-plan MCP-action quota** — the total number of successful agent actions your billing period allows. Exhaust it and calls return `429` until the next renewal (see the Authentication & Scopes page).
</Warning>

A blanket per-token throttle would regress existing personal- and bot-token integrations, and the plan quota already bounds total usage — so a dedicated per-token rate limit is a later, deploy-time step rather than a runtime feature. Design for the quota now; treat any future rate limiting as additive.

## On the roadmap

Forward-looking, in rough order:

<Steps>
  <Step title="Intent-level flow creation">
    A create-from-intent path where an agent describes a goal and the server-side Designer compiles the graph — returning a summary and a preview link, never the graph itself. Keeps the IP boundary intact.
  </Step>

  <Step title="Automation tools">
    Wiring `automation:manage` to real endpoints (rules, macros, canned responses) so the reserved scope becomes live.
  </Step>

  <Step title="Per-token rate limiting & audit">
    A per-minute throttle alongside the plan quota, plus per-key usage and audit views in the Console.
  </Step>

  <Step title="Wider catalog">
    More thin tool wrappers over the existing REST surface as each one clears its safety review.
  </Step>
</Steps>

<Card title="Authentication & Scopes" icon="key" href="/ai-agents/authentication">
  How scopes are enforced today, including the default-deny model and the plan quota.
</Card>