@agent-native/core 0.122.4 → 0.123.0

package/docs/content/file-uploads.mdx

@@ -187,6 +187,50 @@ if (result) {
 }
 ```
 
+## Resumable / Streaming Uploads {#resumable}
+
+A provider can optionally implement a `resumable` block on `FileUploadProvider` for uploads that need to stream to storage as data arrives instead of buffering the whole file first — the Clips template uses this to relay a recording to storage chunk-by-chunk while it is still being recorded, rather than assembling the full blob after the recorder stops.
+
+```ts
+interface FileUploadProvider {
+  // ...id, name, isConfigured, upload...
+
+  resumable?: {
+    startSession(
+      filename: string,
+      mimeType: string,
+      maxBytes: number,
+    ): Promise<ResumableUploadSession>;
+    relayChunk(
+      session: ResumableUploadSession,
+      contentRange: string,
+      bytes: Uint8Array,
+      options?: { mimeType?: string },
+    ): Promise<ResumableChunkResult>;
+    completeSession(
+      session: ResumableUploadSession,
+      filename: string,
+      options?: { stableUrl?: boolean; recordAsset?: boolean },
+    ): Promise<string>;
+    // Best-effort provider cleanup for a session the caller will not resume.
+    abortSession?(session: ResumableUploadSession): Promise<void>;
+  };
+}
+
+interface ResumableUploadSession {
+  sessionId: string; // Provider-specific: GCS Location URI, S3 UploadId, etc.
+  meta: Record<string, unknown>; // Provider state carried between calls
+}
+
+interface ResumableChunkResult {
+  ok: boolean;
+  status: number;
+  updatedMeta?: Record<string, unknown>; // Merged back into the stored session
+}
+```
+
+When `resumable` is present, callers that stream data in (like a recorder) call `startSession` once, `relayChunk` repeatedly as bytes arrive, and `completeSession` when the stream ends — instead of the single buffered `upload()` call. A provider with no `resumable` block only ever sees the buffered path; implement it only when your storage backend has a native chunked/resumable upload API (S3 multipart, GCS resumable uploads, etc.) worth exposing.
+
 ## What's next
 
 - [**Database**](/docs/database) — why binary blobs stay out of SQL and go through this provider abstraction instead

package/docs/content/frames.mdx

@@ -77,8 +77,8 @@ The embedded panel is the agent sidebar your app renders. It ships with
 `@agent-native/core` — there is no separate package to install — and is the same
 component in dev and prod.
 
-- Exported as `AgentPanel` from `@agent-native/core/client`, with a
-  production-only variant `ProductionAgentPanel`.
+- Exported as `AgentPanel` from `@agent-native/core/client`, or wrap your
+  whole layout with `AgentSidebar` — see [Drop-in Agent](/docs/drop-in-agent).
 - Provides the full Chat / CLI / Resources surface, so the agent input stays on
   the shared composer stack used everywhere else in the framework.
 - Reads `application_state.navigation` every turn, so it already knows which

package/docs/content/generative-ui.mdx

@@ -6,6 +6,14 @@ search: "generative UI inline extension render-inline-extension create-extension
 
 # Generative UI
 
+<Callout tone="info">
+
+**Developer page.** This page is for developers building agent-generated inline UI. For the end-user experience of chat, see [Using Your Agent](/docs/using-your-agent).
+
+</Callout>
+
+Ask for something like "give me sliders to tune these thresholds" or "let me pick from these options," and the agent writes and renders that control directly inside the chat transcript — no page reload, no separate app.
+
 Generative UI is the chat-native path for interactive surfaces the agent creates
 at runtime. Instead of replying with only prose or a static table, the agent can
 render a sandboxed Alpine.js/Tailwind mini-app directly inside the transcript:

package/docs/content/getting-started.mdx

@@ -8,7 +8,9 @@ description: "Create a chat-first agentic app, add an action, render structured
 Agent-Native is for agentic applications: apps where the AI agent and the UI
 share the same [actions](/docs/actions), SQL data, and application state. Start
 with chat so users can talk to the agent immediately, then add the app surfaces
-your workflow earns.
+your workflow earns. New to the concept rather than the code? Read
+[What Is Agent-Native?](/docs/what-is-agent-native) first — this page is the
+hands-on build path.
 
 The quickest way in is the **Chat template**: a minimal app that gives you a
 working AI chat interface, durable threads, auth, and an `actions/` directory
@@ -56,26 +58,35 @@ terminal output.
 When the app starts, you might find yourself on the login screen rather than in the app. In this case, just sign up with a made up login to satisfy the login screen.
 For local development, no email verification is actually required.
 
+> **Want to attach a real debugger?** Run `agent-native dev --inspect` (or
+> `--inspect-brk[=<port>]`) instead of `pnpm dev` to attach the Node inspector
+> to the dev server, on port `9229` by default. Override the dev runner with
+> the `NITRO_DEV_RUNNER` env var if your setup needs a different one.
+
 ### If you want a different type of app
 
 This guide uses the Chat template because it is the shortest path
 to an agentic application: the agent can act on day one, and you have a real app
-surface to grow from. However, if you want to create a different kind of app, run `create` with no flags for the CLI picker for domain templates and advanced app shapes:
+surface to grow from. However, if you want to create a different kind of app, run `create` with no flags:
 
 ```bash
 npx @agent-native/core@latest create my-app
 ```
 
-## 2. Connect an AI engine {#connect-ai}
-
-The agent chat can't respond until you connect an AI engine. After you're logged in, click the **Connect AI** button.
+The CLI first asks **How do you want to start?** with three choices: **Chat**
+(what this guide uses), **Full template(s)**, or **Headless**. Only picking
+**Full template(s)** takes you to the domain-template multi-select (Mail,
+Calendar, Forms, Analytics, Plan, and more) — Chat and Headless each scaffold a
+single standalone app directly, with no further picker.
 
-You have two options:
+## 2. Connect an AI engine {#connect-ai}
 
-**Option A: Connect Builder.** Click **Connect Builder.io**, choose the Builder Space, and click the **Authorize** button. You don't have to manually provide any keys.
+The agent chat can't respond until you connect an AI engine. After you're logged in, click the **Connect AI** button and pick one of two paths:
 
-**Option B: Add your own keys.** Enter your Anthropic or OpenAI API key. You can get an
-Anthropic key at [console.anthropic.com](https://console.anthropic.com).
+| Path                   | Steps                                                                                                                                      |
+| ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
+| **Connect Builder**    | Click **Connect Builder.io**, choose the Builder Space, then click **Authorize**. No keys to manage yourself.                              |
+| **Bring your own key** | Enter your Anthropic or OpenAI API key in the Setup panel. Get an Anthropic key at [console.anthropic.com](https://console.anthropic.com). |
 
 Alternatively, create a `.env` file in the `my-app/` directory (the same
 directory that contains `package.json`) before running `pnpm dev`:
@@ -602,24 +613,36 @@ with a few saved rows:
 
 ## 7. Extend the navigation {#extend-navigation}
 
-The sidebar is configured in `app/config/nav.ts`. Open it and add an entry for
-the Text analyses page:
+The sidebar's links are a plain array in `app/components/layout/Sidebar.tsx`,
+not a separate config file. Open it and add an entry for the Text analyses
+page next to the existing Chat entry:
+
+```tsx filename="app/components/layout/Sidebar.tsx"
+import { IconList, IconMessageCircle } from "@tabler/icons-react";
 
-```ts filename="app/config/nav.ts"
-export const navConfig = [
+const navItems = [
   {
-    label: "Chat",
+    icon: IconMessageCircle,
+    labelKey: "navigation.chat",
     href: "/",
-    icon: "chat",
+    view: "chat",
   },
   {
-    label: "Text analyses",
+    icon: IconList,
+    labelKey: "navigation.textAnalyses",
     href: "/text-analyses",
-    icon: "list",
+    view: "text-analyses",
   },
 ];
 ```
 
+`icon` takes an imported Tabler icon component, not a string name. `labelKey`
+looks up a string in the i18n catalog (`app/i18n/en-US.ts` and the other
+locale files); an unregistered key still renders — it falls back to a
+humanized version of the key (`navigation.textAnalyses` becomes "Text
+analyses") — but add it to the catalogs if you want the label translated. See
+[Internationalization](/docs/internationalization).
+
 Save the file. The dev server picks up the change automatically and the sidebar
 updates without a restart.
 
@@ -665,6 +688,10 @@ customize the app from there.
 
 ## What's next {#next}
 
+- **[What Is Agent-Native?](/docs/what-is-agent-native)**: the vision and the
+  case for building this way.
+- **[Key Concepts](/docs/key-concepts)**: the architecture underneath this
+  tutorial — SQL, actions, live sync, context awareness.
 - **[Actions](/docs/actions)**: schemas, auth, approvals, hooks, and transport.
 - **[Native Chat UI](/docs/native-chat-ui)**: render action results as tables,
   charts, and typed cards.
@@ -677,3 +704,4 @@ customize the app from there.
 - **[Agent Surfaces](/docs/agent-surfaces)**: chat, inline UI, app pages,
   embedded sidecars, automation, and external agents.
 - **[Deployment](/docs/deployment)**: put your app on your own domain.
+- **[FAQ](/docs/faq)**: quick answers on cost, hosting, models, and templates.

package/docs/content/human-approval.mdx

@@ -78,6 +78,15 @@ The paused tool returns a result telling the model the turn is paused and not to
 
 On `approval_required`, the chat UI renders an **Approve / Deny** affordance on the paused tool call. This is wired automatically in `AssistantChat` — you don't build it per template.
 
+<WireframeBlock id="doc-block-humanapprovalwf1">
+  <Screen
+    surface="panel"
+    html={
+      "<div style='display:flex;flex-direction:column;min-height:200px;box-sizing:border-box;padding:16px;gap:12px'><div class='wf-card' style='display:flex;flex-direction:column;gap:8px'><div style='display:flex;align-items:center;gap:8px'><span class='wf-pill warn'>Needs approval</span><strong>send-email</strong></div><div style='display:flex;flex-direction:column;gap:2px'><span class='wf-muted'>to: alex@acme.com</span><span class='wf-muted'>subject: Following up on the proposal</span></div><div style='display:flex;gap:8px'><button>Deny</button><button class='primary'>Approve</button></div></div></div>"
+    }
+  />
+</WireframeBlock>
+
 - **Approve** re-issues the turn (an ordinary continuation message) carrying the call's key in `approvedToolCalls: [approvalKey]`. On the re-issued turn, the gate sees the key in the approved set and lets that specific call run normally.
 - **Deny** dismisses the affordance locally; nothing is re-issued, so the action never runs.
 

package/docs/content/integrations.mdx

@@ -357,7 +357,7 @@ but need provider or administrator setup before a generic connection can work.
 | [monday.com](https://developer.monday.com/api-reference/docs/build-on-monday-with-ai)                                                                                   | OAuth                  | Ready · preflight only             | `https://mcp.monday.com/mcp`              | Choose the workspace and permissions to share during authorization.                                                                                                                                                               |
 | [Webflow](https://developers.webflow.com/mcp/reference/getting-started)                                                                                                 | OAuth                  | Ready · preflight only             | `https://mcp.webflow.com/mcp`             | Designer capabilities may install Webflow's Bridge App; Data API access is separate.                                                                                                                                              |
 | [PayPal](https://developer.paypal.com/ai-tools/mcp-server/)                                                                                                             | OAuth                  | Ready · preflight only             | `https://mcp.paypal.com/sse`              | Review merchant permissions before authorizing the remote server.                                                                                                                                                                 |
-| [Box](https://developer.box.com/guides/box-mcp)                                                                                                                         | Manual setup           | Beta · restricted                  | `https://mcp.box.com`                     | An administrator must enable Box MCP; custom clients also need credentials, a redirect URI, and approved scopes.                                                                                                                  |
+| [Box](https://developer.box.com/guides/box-mcp)                                                                                                                         | Manual setup           | Provider setup · restricted        | `https://mcp.box.com`                     | An administrator must enable Box MCP; custom clients also need credentials, a redirect URI, and approved scopes.                                                                                                                  |
 | [Netlify](https://docs.netlify.com/build/build-with-ai/agent-setup-guides/agent-setup-overview/)                                                                        | OAuth                  | Ready · preflight only             | `https://netlify-mcp.netlify.app/mcp`     | Review site and team permissions before completing OAuth.                                                                                                                                                                         |
 | [Zapier MCP](https://help.zapier.com/hc/en-us/articles/36265392843917-Use-Zapier-MCP-with-your-client)                                                                  | Header / token         | User-created server · restricted   | `https://mcp.zapier.com/api/v1/connect`   | Create the MCP server in Zapier, then paste its generated bearer token into the header field.                                                                                                                                     |
 
@@ -393,6 +393,7 @@ workspace provider catalog currently includes these providers:
 | HubSpot      | OAuth preferred; private-token fallback     | CRM records and engagement history          | OAuth is preferred for new connections.                                        |
 | Jira Cloud   | OAuth preferred; API-token fallback         | Projects, issues, and sprints               | OAuth discovers the site; token fallback needs the site URL and account email. |
 | Sentry       | OAuth preferred; auth/server-token fallback | Error tracking and performance              | Token fallback is useful for self-hosted or local Sentry.                      |
+| Salesforce   | OAuth                                       | CRM accounts, contacts, opportunities       | OAuth is the only supported connection mode; no token fallback.                |
 | Granola      | API key                                     | Meeting notes and transcripts               | Respect the visibility of the connected Granola workspace.                     |
 | Clips        | Built-in                                    | Agent-Native recordings and transcripts     | No external credential is required for the framework's own Clips exports.      |
 | Generic      | Manual/custom                               | Webhooks, CSV exports, and transcript drops | Use when a source does not need a first-class provider yet.                    |
@@ -407,8 +408,8 @@ discovery, documentation lookup, and safe HTTP requests. It currently includes
 these built-in providers:
 
 - **OAuth-backed or workspace-granted:** GitHub, Figma, Gmail, Google
-  Calendar, Google Drive, Google Slides, HubSpot, Jira Cloud, Notion, and
-  Sentry.
+  Calendar, Google Drive, Google Slides, HubSpot, Jira Cloud, Notion,
+  Salesforce, and Sentry.
 - **Google service-account:** BigQuery, Google Analytics 4, and Google Cloud
   APIs.
 - **API key or bearer token:** Apollo, Clay, Common Room, Granola, Grafana,

package/docs/content/internationalization.mdx

@@ -15,11 +15,8 @@ English when an app has not translated a string yet.
 Use the provider through `AppProviders`:
 
 ```tsx
-import {
-  AppProviders,
-} from "@agent-native/core/client/hooks"import {
-  getLocaleInitScript,
-} from "@agent-native/core/client/i18n"
+import { AppProviders } from "@agent-native/core/client/hooks";
+import { getLocaleInitScript } from "@agent-native/core/client/i18n";
 import { i18nCatalog } from "./i18n";
 
 const LOCALE_INIT_SCRIPT = getLocaleInitScript();
@@ -72,12 +69,8 @@ Use `useT()` for interface strings and put `<LanguagePicker />` on the app's
 the header language icon is only a shortcut.
 
 ```tsx
-import {
-  LanguagePicker,
-  useT,
-} from "@agent-native/core/client/i18n"import {
-  openAgentSettings,
-} from "@agent-native/core/client/navigation"
+import { LanguagePicker, useT } from "@agent-native/core/client/i18n";
+import { openAgentSettings } from "@agent-native/core/client/navigation";
 function SettingsPage() {
   const t = useT();
   return (

package/docs/content/key-concepts.mdx

@@ -437,7 +437,7 @@ Adopting the framework is valuable mostly because of what you stop having to bui
 - **Drop-in React components.** `<AgentPanel />` and `<AgentSidebar />` render chat + resources anywhere in your app. See [Drop-in Agent](/docs/drop-in-agent).
 - **BYO agent chat runtimes.** The same chat UI can sit on top of OpenAI Agents, OpenAI Responses, Claude Agent SDK, Vercel AI SDK, AG-UI, or your own normalized HTTP stream. See [Native Chat UI](/docs/native-chat-ui#byo-agent-runtimes).
 - **Live sync between agent and UI.** Same-process writes stream immediately over `/_agent-native/events`; a lightweight poll keeps serverless, cron, and cross-process writes convergent. Mutating actions invalidate action-backed queries automatically, so agent-created records appear without a manual refresh. See [Live Sync](#polling-sync) below.
-- **Auth, orgs, RBAC.** Better Auth with orgs/members/roles is wired in for every template. See [Authentication](/docs/authentication).
+- **Auth, orgs, RBAC.** Better Auth with orgs/members/roles is wired in for every template. See [Authentication](/docs/authentication). Building for more than one user? Start with [Organizations, Teams & Permissions](/docs/organizations-teams-permissions).
 - **Context awareness.** The agent always knows what the user is looking at through the `navigation` app-state key. See [Context Awareness](/docs/context-awareness).
 - **MCP client + server, both directions.** The app ingests MCP servers (local, remote, hub-shared) _and_ exposes its own actions as an MCP server. See [MCP Clients](/docs/mcp-clients) and [MCP Protocol](/docs/mcp-protocol).
 - **Inter-app delegation.** Agents in different apps talk over [A2A](/docs/a2a-protocol). Same-origin deploys skip JWT; cross-origin uses a shared `A2A_SECRET`.

package/docs/content/local-file-mode.mdx

@@ -139,3 +139,8 @@ After the first connection and sync, verify:
 The old two-mode architecture is retired. Local folders are now adapters around
 the global database model—which is less dramatic than a mode switch, and much
 less likely to leave half the product living in a parallel universe.
+
+## What's next
+
+- [**Database**](/docs/database) — the SQL model every Content page and space is backed by, mode switch or not
+- [**Content**](/docs/template-content) — the app this connects to: spaces, the Files database, and the editor built on top of it

package/docs/content/mcp-apps.mdx

@@ -245,7 +245,8 @@ Test MCP Apps with the lightweight fixtures around `embedApp()` and `McpAppRende
 
 ## What's next {#whats-next}
 
-- [External Agents](/docs/external-agents) — connecting Claude, ChatGPT, Codex, and Cursor to hosted apps; MCP Apps compatibility matrix; catalog tiers; deep links.
+- [External Agents](/docs/external-agents) — connecting Claude, ChatGPT, Codex, and Cursor to hosted apps; deep links.
+- [External Agents Catalog](/docs/external-agents-catalog) — catalog tiers, the MCP Apps compatibility matrix, and the `link` builder for template authors.
 - [MCP Server](/docs/mcp-protocol) — the auto-mounted MCP server, auth, tools, and `ask-agent`.
 - [Actions](/docs/actions) — `defineAction`, the `link` builder, `publicAgent`.
 - [Generative UI](/docs/generative-ui) — generated inline UI inside the app's own chat.

package/docs/content/mcp-clients.mdx

@@ -145,6 +145,18 @@ Use concise, explicit setup copy for the sensitive built-ins:
 | GET    | `/_agent-native/mcp/builtin` | List built-in capabilities, enabled scopes, merged ids, and live status.   |
 | POST   | `/_agent-native/mcp/builtin` | Update a scope. Body: `{ scope, enabledIds }` or `{ scope, id, enabled }`. |
 
+<Endpoint id="doc-block-mcpc-builtin" method="GET" path="/_agent-native/mcp/builtin" summary="List built-in capability state for the current user/org scope" responses={[
+  {
+    "status": "200",
+    "description": "Built-in capabilities (chrome-devtools, playwright, computer-use), which scopes have them enabled, merged server ids, and live connection status.",
+    "example": "{\n  \"capabilities\": [\n    { \"id\": \"playwright\", \"enabledScopes\": [\"user\"], \"connected\": true }\n  ]\n}"
+  }
+]}>
+
+Reports which local-development built-ins (Chrome DevTools, Playwright, Computer Use) are enabled for the current user or organization, and whether they're currently connected. `POST` to the same path with `{ scope, enabledIds }` or `{ scope, id, enabled }` to change a scope's setting.
+
+</Endpoint>
+
 ## Adding a local MCP server {#adding-a-server}
 
 Create `mcp.config.json` at your workspace root (or at an individual app root — workspace root wins when both exist):
@@ -277,7 +289,7 @@ export default {
 
 Preset ids are `context7`, `sentry`, `notion`, `granola`, `semgrep`, `linear`,
 `atlassian`, `supabase`, `neon`, `stripe`, `cloudflare`, `gitlab`, `figma`,
-`vercel`, `github`, `slack`, `asana`, `hubspot`, `intercom`, `monday`,
+`canva`, `vercel`, `github`, `slack`, `asana`, `hubspot`, `intercom`, `monday`,
 `webflow`, `paypal`, `box`, `netlify`, and `zapier`.
 
 The directory distinguishes endpoints that support the framework's generic
@@ -387,6 +399,25 @@ Under the hood these servers are persisted in the framework's `settings` table u
 | POST   | `/_agent-native/mcp/servers/:id/test?scope=user\|org` | Dry-run the existing server's connect + list-tools.                    |
 | POST   | `/_agent-native/mcp/servers/test`                     | Dry-run an arbitrary URL before persisting. Body: `{ url, headers? }`. |
 
+<Endpoint id="doc-block-mcpc-servers" method="POST" path="/_agent-native/mcp/servers" summary="Add a remote MCP server for the current user or organization" auth="Authenticated session; org-scope writes require owner or admin." request={{
+  "contentType": "application/json",
+  "example": "{\n  \"scope\": \"user\",\n  \"name\": \"zapier\",\n  \"url\": \"https://mcp.zapier.com/s/abc123/mcp\",\n  \"headers\": { \"Authorization\": \"Bearer sk-your-key-here\" }\n}"
+}} responses={[
+  {
+    "status": "200",
+    "description": "Server saved and hot-reloaded into the running MCP manager; its tools appear to the agent on the next message.",
+    "example": "{ \"id\": \"zapier\", \"scope\": \"user\", \"toolCount\": 6 }"
+  },
+  {
+    "status": "400",
+    "description": "Invalid URL (non-HTTPS and not localhost) or malformed headers."
+  }
+]}>
+
+Adds a remote MCP server for `scope: "user"` (personal) or `scope: "org"` (team, owner/admin only). The addition hot-reloads into the running MCP manager — no restart — and the new `mcp__<scope>-<name>__*` tools become searchable via `tool-search` immediately. `DELETE /_agent-native/mcp/servers/:id?scope=user|org` removes one the same way.
+
+</Endpoint>
+
 Stdio servers are still a no-op outside Node runtimes, but remote HTTP MCP servers work in any environment with `fetch` — including desktop production builds.
 
 ## Shared MCP servers via a hub {#hub}

package/docs/content/mcp-protocol.mdx

@@ -180,7 +180,7 @@ If an action declares `mcpApp`, the server advertises the official MCP Apps exte
 - Hosts that render MCP Apps show the UI inline; hosts that don't can still call the tool and use the deep-link fallback.
 - Product UIs should use `embedApp()` so the inline surface is the real React app route, or a focused route that renders a shared React component such as an Analytics chart — never a separate plain-HTML implementation.
 - The server emits both standard MCP Apps metadata and ChatGPT Apps SDK compatibility metadata so app-capable hosts find the same `ui://` resource.
-- The current official extension matrix includes Claude, Claude Desktop, VS Code GitHub Copilot, Goose, Postman, MCPJam, ChatGPT, and Cursor. Host support varies by version and plan — see the [External Agents MCP Apps notes](/docs/external-agents#mcp-apps-compatibility) for the user-facing guidance.
+- The current official extension matrix includes Claude, Claude Desktop, VS Code GitHub Copilot, Goose, Postman, MCPJam, ChatGPT, and Cursor. Host support varies by version and plan — see the [External Agents Catalog — MCP Apps compatibility](/docs/external-agents-catalog#mcp-apps-compatibility) for the user-facing guidance.
 
 ### MCP App embed bridge {#mcp-app-embed-bridge}
 
@@ -195,7 +195,7 @@ See [MCP Apps](/docs/mcp-apps#mcp-app-bridge) for the full embed bridge details
 
 ## Tools {#tools}
 
-Every caller gets a **compact catalog by default** (template-declared app actions plus the cross-app builtins), with the full action surface served only on explicit opt-in and `tool-search` always available to reach the rest. See [External Agents → Catalog tiers](/docs/external-agents#catalog-tiers) for the full explanation.
+Every caller gets a **compact catalog by default** (template-declared app actions plus the cross-app builtins), with the full action surface served only on explicit opt-in and `tool-search` always available to reach the rest. See [External Agents Catalog → Catalog tiers](/docs/external-agents-catalog#catalog-tiers) for the full explanation.
 
 Each action maps directly to one MCP tool:
 
@@ -423,7 +423,8 @@ Claude Code calls: ask-agent(message: "Prepare a full breakdown of Q3 signups by
 
 ## What's next {#whats-next}
 
-- [**External Agents**](/docs/external-agents) — the recommended connect flow, catalog tiers, and per-host setup
+- [**External Agents**](/docs/external-agents) — the recommended connect flow and per-host setup
+- [**External Agents Catalog**](/docs/external-agents-catalog) — catalog tiers and tool exposure for template authors
 - [**MCP Apps**](/docs/mcp-apps) — inline UI resources for hosts that render them
 - [**MCP Clients**](/docs/mcp-clients) — the other direction: your app consuming external MCP servers
 - [**A2A Protocol**](/docs/a2a-protocol) — the sibling protocol for agent-to-agent calls