@agent-native/core 0.98.16 → 0.99.0

package/docs/content/locales/zh-TW/mcp-clients.mdx

@@ -245,6 +245,29 @@ MCP 工具僅在 Node 執行時啟用 - Cloudflare Workers 和其他邊緣
 
 MCP（模型脈絡協議）伺服器為您的代理提供新的能力 - 例如連線到 Zapier、Cloudflare、Composio 或您公司的內部工具。連線後，代理可以像使用內建工具一樣使用這些工具。
 
+預設 ID 包括 `context7`、`sentry`、`notion`、`semgrep`、`linear`、
+`atlassian`、`supabase`、`neon` 和 `stripe`。
+
+### Atlassian / Jira
+
+Atlassian 預設使用 Atlassian Rovo MCP 的 OAuth 2.1 端點
+`https://mcp.atlassian.com/v1/mcp/authv2`，並提供 Jira 和 Confluence
+工具。建立 Jira 議題需要具備允許寫入 Jira 的 Atlassian 權限；使用者仍然只能
+看到其 Atlassian 帳戶有權存取的專案和內容。
+
+Atlassian 組織管理員可以控制是否允許 OAuth 用戶端連線。連線之前，管理員可能
+需要將應用程式的實際 HTTPS 來源新增至 **Atlassian Administration → Rovo →
+Rovo MCP server → Domains** 下的受信任網域清單，並在 **Permissions** 中啟用
+所需的 **Read**、**Write** 和 **Search** 權限。該網域必須是 Agent-Native
+應用程式實際執行的主機；除非 `https://builder.io/**` 是部署的實際來源，否則
+不要將其複製到其他部署。請參閱 Atlassian 的 [Rovo MCP 設定指南](https://developer.atlassian.com/cloud/rovo-mcp/guides/getting-started/)
+和[管理員控制說明](https://support.atlassian.com/security-and-access-policies/docs/control-atlassian-rovo-mcp-server-settings/)。
+
+目錄會提供端點和設定指引。通用設定表單會儲存端點和選用的加密標頭，但無法取代
+Atlassian 的互動式 OAuth 同意流程。當 Atlassian 要求互動式 OAuth 時，請使用
+支援 OAuth 的 MCP 用戶端或執行階段。如果供應商或執行階段支援靜態 Bearer
+權杖，請遵循其核准的密鑰管理流程，切勿將權杖貼到提示詞或已提交的設定中。
+
 ### 如何連線遠端 MCP 伺服器
 
 1. **伺服器名稱** - 供您自己參考的簡短標籤（例如“zapier”、“slack-tools”）。
@@ -263,7 +286,7 @@ MCP（模型脈絡協議）伺服器為您的代理提供新的能力 - 例如
 
 在正在執行的 MCP 管理器中新增和刪除熱重載 — 無需重新啟動行程，也無需重新啟動伺服器。新的 `mcp__<scope>-<name>__*` 工具將在下一條訊息中向代理顯示，並且可透過 `tool-search` 進行搜尋。
 
-HTTPS URL 在任何地方都被接受； plain `http://` 在開發過程中僅允許用於 `localhost`。可選的驗證作為不記名權杖在每個請求上透過 `Authorization: Bearer …` 傳送。
+HTTPS URL 在任何地方都被接受； plain `http://` 在開發過程中僅允許用於 `localhost`。可選的驗證作為不記名權杖在每個請求上透過 `Authorization: Bearer …` 傳送。僅支援 OAuth 的供應商（包括 Atlassian Rovo MCP）必須使用供應商的 OAuth 流程，而不能使用靜態標頭。
 
 在底層，這些伺服器以 `u:<email>:mcp-servers-remote`（個人）或 `o:<orgId>:mcp-servers-remote`（團隊）鍵儲存在框架的 `settings` 表中，並在啟動時與 `mcp.config.json` 合併。
 
@@ -292,7 +315,9 @@ Dispatch 是傳統的中心 - 它已經跨應用進行協調。
   <div class="diagram-panel center" data-rough>
     <span class="diagram-pill accent">Dispatch hub</span
     ><small class="diagram-muted">組織範圍 MCP 伺服器</small
-    ><small class="diagram-muted"><code>GET /mcp/hub/servers</code></small>
+    ><small class="diagram-muted"
+      ><code>GET /_agent-native/mcp/hub/servers</code></small
+    >
   </div>
   <div class="diagram-col arrows">
     <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
@@ -454,7 +479,7 @@ Reports which configured servers connected, the total live tool count, the merge
 
 個別 MCP 伺服器故障永遠不會導致代理關閉：
 
-- 設定錯誤的 `command` → 伺服器被跳過，其錯誤出現在 `errors.<server-id>` 下的 `/mcp/status` 中，而其他所有伺服器繼續工作。
+- 設定錯誤的 `command` → 伺服器被跳過，其錯誤出現在 `errors.<server-id>` 下的 `/_agent-native/mcp/status` 中，而其他所有伺服器繼續工作。
 - `node_modules` 中缺少 MCP SDK → 所有 MCP 功能都會被跳過並出現警告；代理聊天可以使用零 MCP 工具繼續工作。
 - 在邊緣執行時中執行 → MCP 用戶端是無操作的。
 

package/docs/content/locales/zh-TW/mcp-protocol.mdx

@@ -22,7 +22,7 @@ MCP 是用於將 AI 工具連線到外部功能的標準協議。當您部署 Ag
 
 關鍵概念：
 
-- **自動安裝** — 每個應用都免費獲得 `/_agent-native/mcp`，無需設定
+- **自動安裝** — 每個應用都免費獲得 `/mcp`，無需設定
 - **Streamable HTTP** — 在標準 HTTP (POST + SSE) 上使用現代 MCP 傳輸
 - **相同的 actions** — 為代理聊天和 A2A 提供支援的完全相同的操作註冊表
 - **`ask-agent` 工具** — 一種元工具，可委托給完整代理迴圈來執行複雜工作
@@ -41,7 +41,7 @@ MCP 是用於將 AI 工具連線到外部功能的標準協議。當您部署 Ag
   </div>
   <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
   <div class="diagram-panel">
-    <span class="diagram-pill accent">POST /_agent-native/mcp</span
+    <span class="diagram-pill accent">POST /mcp</span
     ><small class="diagram-muted">Streamable HTTP</small
     ><small class="diagram-muted"
       >initialize &rarr; tools/list &rarr; tools/call</small
@@ -94,7 +94,7 @@ MCP 是用於將 AI 工具連線到外部功能的標準協議。當您部署 Ag
 | **最適合**   | 呼叫您的應用的外部工具                                              | 代理間通信                             |
 | **協議**     | MCP 可流式傳輸 HTTP                                                 | JSON-RPC 2.0                           |
 | **工具發現** | `tools/list`                                                        | `/.well-known/agent-card.json`的代理卡 |
-| **端點**     | `/_agent-native/mcp`                                                | `/_agent-native/a2a`                   |
+| **端點**     | `/mcp`                                                              | `/_agent-native/a2a`                   |
 | **支援**     | Claude、ChatGPT、Claude Code、Cursor、Codex、Cowork 和其他 MCP 主機 | 其他 Agent-Native 應用                 |
 | **執行**     | 直接工具呼叫（無需額外的 LLM）                                      | 完整代理迴圈（LLM 推理）               |
 
@@ -105,7 +105,7 @@ MCP 是用於將 AI 工具連線到外部功能的標準協議。當您部署 Ag
 對於建議的單指令設定，請使用 [External Agents](/docs/external-agents)。如果您為支援 OAuth 的用戶端手寫 MCP 設定，請將您的應用新增為不帶靜態標頭的遠端 MCP 伺服器：
 
 ```bash
-claude mcp add --transport http mail https://mail.example.com/_agent-native/mcp
+claude mcp add --transport http mail https://mail.example.com/mcp
 ```
 
 或者在 `.mcp.json`（專案範圍）或 `~/.claude.json`（使用者範圍）中手動寫入條目：
@@ -116,7 +116,7 @@ claude mcp add --transport http mail https://mail.example.com/_agent-native/mcp
   "mcpServers": {
     "mail": {
       "type": "http",
-      "url": "https://mail.example.com/_agent-native/mcp",
+      "url": "https://mail.example.com/mcp",
     },
   },
 }
@@ -135,12 +135,12 @@ Claude Code calls: draft-email(to: "john@example.com", subject: "Q3 Report", bod
 任何支援 Streamable HTTP 傳輸的 MCP 用戶端都可以連線。端點是：
 
 ```
-POST https://your-app.example.com/_agent-native/mcp
+POST https://your-app.example.com/mcp
 ```
 
 伺服器支援標準 MCP 握手：`initialize`→`initialized`→`tools/list`→`tools/call`。
 
-<Endpoint id="doc-block-1qz0910" title={"MCP 端點"} summary={"每個 Agent-Native 應用程式都會公開自動安裝的 Streamable HTTP 端點。"} method="POST" path="/_agent-native/mcp" summary={"MCP 可流式 HTTP 端點"} auth="Standard remote MCP OAuth (Bearer access token), connect-minted JWT, or static ACCESS_TOKEN/ACCESS_TOKENS" params={[
+<Endpoint id="doc-block-1qz0910" title={"MCP 端點"} summary={"每個 Agent-Native 應用程式都會公開自動安裝的 Streamable HTTP 端點。"} method="POST" path="/mcp" summary={"MCP 可流式 HTTP 端點"} auth="Standard remote MCP OAuth (Bearer access token), connect-minted JWT, or static ACCESS_TOKEN/ACCESS_TOKENS" params={[
   {
     "name": "Authorization",
     "in": "header",
@@ -204,18 +204,33 @@ Auto-mounted on every app. Speaks the standard MCP handshake (`initialize` → `
 
 除了單獨的操作工具外，每個 MCP 伺服器還包含一個 `ask-agent` 元工具。這會向應用程式的 AI 代理傳送一條自然語言訊息並返回回應。
 
+託管 MCP 請求使用有上限的行內等待，讓長時間執行的代理迴圈不會讓單一 `tools/call` 一直開啟，直到用戶端或閘道器逾時為止。選用的 `async` 參數會啟動持久任務並立即返回；若未提供，伺服器會短暫等待快速完成，若仍有工作待處理，則會返回任務控點。託管等待上限為 25 秒。
+
 使用 `ask-agent` 執行複雜工作，受益於代理的推理和脈絡：
 
 ```json
 {
   "name": "ask-agent",
   "arguments": {
-    "message": "Draft a follow-up email to the Q3 planning thread with John, summarizing the action items we discussed"
+    "message": "Draft a follow-up email to the Q3 planning thread with John, summarizing the action items we discussed",
+    "async": true
+  }
+}
+```
+
+代理執行與互動式聊天相同的迴圈 — 它可以呼叫多個工具、推理脈絡並生成深思熟慮的回應。尚未完成的任務會返回包含 `taskId`、`status`、`pollAfterMs` 的 JSON，以及：
+
+```json
+{
+  "poll": {
+    "tool": "ask_app_status",
+    "arguments": { "app": "mail", "taskId": "task_123" }
   }
 }
 ```
 
-代理執行與互動式聊天相同的迴圈 - 它可以呼叫多個工具、推理脈絡並生成深思熟慮的回應。
+請使用這些引數呼叫 `ask_app_status`，直到任務進入終止狀態。Dispatch 應用程式自有的
+`ask_app` 使用相同的持久任務與狀態合約，並在提交與輪詢時都會檢查所選應用程式的授權。
 
 ## 驗證 {#authentication}
 
@@ -233,7 +248,7 @@ MCP 端點支援標準遠端 MCP OAuth 以及現有的不記名權杖後備：
 對於支援 OAuth 的 MCP 主機，設定不帶靜態標頭的遠端伺服器 URL：
 
 ```bash
-claude mcp add --transport http agent-native https://dispatch.agent-native.com/_agent-native/mcp
+claude mcp add --transport http agent-native https://dispatch.agent-native.com/mcp
 ```
 
 第一個未經驗證的 MCP 請求收到：
@@ -249,9 +264,9 @@ WWW-Authenticate: Bearer resource_metadata="https://dispatch.agent-native.com/.w
 | ----------------------------------------- | ---------------------------- |
 | `/.well-known/oauth-protected-resource`   | RFC 9728 受保護資源中繼資料  |
 | `/.well-known/oauth-authorization-server` | OAuth 授權伺服器中繼資料     |
-| `/_agent-native/mcp/oauth/register`       | 動態公開用戶端註冊           |
-| `/_agent-native/mcp/oauth/authorize`      | 瀏覽器授權+同意              |
-| `/_agent-native/mcp/oauth/token`          | 授權程式碼和重新整理權杖授予 |
+| `/mcp/oauth/register`                     | 動態公開用戶端註冊           |
+| `/mcp/oauth/authorize`                    | 瀏覽器授權+同意              |
+| `/mcp/oauth/token`                        | 授權程式碼和重新整理權杖授予 |
 
 <Diagram id="doc-block-cy0fgf" title={"OAuth 發現流程"} summary={"401 啟動發現、註冊和 PKCE 授權 → 權杖交換。不記名權杖是受受眾限制和範圍的。"}>
 
@@ -351,7 +366,7 @@ export default defineNitroPlugin(async (nitro) => {
 您在 `analytics.example.com` 部署了分析應用程式。來自 Claude 程式碼：
 
 ```bash
-claude mcp add --transport http analytics https://analytics.example.com/_agent-native/mcp
+claude mcp add --transport http analytics https://analytics.example.com/mcp
 ```
 
 或者在`.mcp.json`中手動新增：
@@ -362,7 +377,7 @@ claude mcp add --transport http analytics https://analytics.example.com/_agent-n
   "mcpServers": {
     "analytics": {
       "type": "http",
-      "url": "https://analytics.example.com/_agent-native/mcp",
+      "url": "https://analytics.example.com/mcp",
     },
   },
 }

package/docs/content/locales/zh-TW/plan-plugin.mdx

@@ -12,7 +12,7 @@ Agent-Native **Plan** 應用程式以一個可安裝的 bundle 提供。一次
 一次安裝即可為您提供：
 
 - **三個 skills** — `/visual-plan`（規範入口點）、`/visual-recap` 和 `/visualize-repo`。
-- **計畫 MCP 連線器** — 針對 `https://plan.agent-native.com` 上的託管應用程式進行註冊（MCP 端點 `https://plan.agent-native.com/_agent-native/mcp`，伺服器名稱 `plan`）。
+- **計畫 MCP 連線器** — 針對 `https://plan.agent-native.com` 上的託管應用程式進行註冊（MCP 端點 `https://plan.agent-native.com/mcp`，伺服器名稱 `plan`）。
 
 <Diagram id="doc-block-6n3so7" title={"三條路由，一攬子"} summary={"通用 CLI、Claude Code 外掛和 Codex 外掛都會安裝同一組 Plan skills 以及託管的 Plan 連線器。"}>
 
@@ -41,7 +41,7 @@ Agent-Native **Plan** 應用程式以一個可安裝的 bundle 提供。一次
   <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
   <div class="diagram-box">
     Plan MCP connector<br /><small class="diagram-muted"
-      >plan.agent-native.com/_agent-native/mcp</small
+      >plan.agent-native.com/mcp</small
     >
   </div>
 </div>
@@ -249,7 +249,7 @@ codex plugin add agent-native-visual-plans@agent-native-apps
 codex mcp login plan   # 瀏覽器中的 OAuth
 ```
 
-安裝後，**啟動新的 Codex 對話串**，以便 skills 和 MCP 工具載入到工作階段中。該外掛附帶一個僅限 URL 的連線器（`[mcp_servers.plan]` → `https://plan.agent-native.com/_agent-native/mcp`）； `codex mcp login plan` 執行 OAuth 流程。如果您更喜歡使用一個指令來同時安裝和驗證，或者需要本機檔案或自託管模式，則上面的通用 CLI 路由也適用於 Codex (`npx @agent-native/core@latest skills add visual-plan --client codex`)。
+安裝後，**啟動新的 Codex 對話串**，以便 skills 和 MCP 工具載入到工作階段中。該外掛附帶一個僅限 URL 的連線器（`[mcp_servers.plan]` → `https://plan.agent-native.com/mcp`）； `codex mcp login plan` 執行 OAuth 流程。如果您更喜歡使用一個指令來同時安裝和驗證，或者需要本機檔案或自託管模式，則上面的通用 CLI 路由也適用於 Codex (`npx @agent-native/core@latest skills add visual-plan --client codex`)。
 
 > **較舊的安裝：**如果您的設定仍然有一個 `agent-native-plans` 條目指向相同的 URL，為 Codex 執行 `npx -y @agent-native/core@latest reconnect https://plan.agent-native.com --client codex`，或者與您的目標 `--client` 執行相同的指令，則將其合併為規範的 `plan` 名稱。
 

package/docs/content/locales/zh-TW/server.mdx

@@ -265,7 +265,7 @@ export default runMigrations(
 | `/_agent-native/extensions/*`    | 執行時擴充功能和擴充功能代理（舊別名：`/_agent-native/tools/*`） |
 | `/_agent-native/integrations/*`  | 訊息傳遞/webhook 整合                                            |
 | `/_agent-native/a2a`             | 代理到代理 JSON-RPC                                              |
-| `/_agent-native/mcp`             | MCP 端點                                                         |
+| `/mcp`                           | MCP 端點                                                         |
 | `/_agent-native/onboarding/*`    | 設定清單                                                         |
 | `/_agent-native/observability/*` | 跟蹤、意見回饋、評估、實驗                                       |
 | `/_agent-native/file-upload`     | 檔案上傳提供者端點                                               |
@@ -460,4 +460,4 @@ const handler = createProductionAgentHandler({
 - [**資料庫**](/docs/database) — 自訂路由和 actions 都會匯入的 `getDb()`/`schema` 模式
 - [**安全性**](/docs/security#access-guards) — `accessFilter`/`assertAccess` 和完整的資料範圍模型
 - [**訊息傳遞**](/docs/messaging) — 傳入 webhook 的標準整合佇列模式
-- [**MCP 通訊協定**](/docs/mcp-protocol) — 此伺服器自動掛載的 `/_agent-native/mcp` 端點
+- [**MCP 通訊協定**](/docs/mcp-protocol) — 此伺服器自動掛載的 `/mcp` 端點

package/docs/content/locales/zh-TW/skills-guide.mdx

@@ -313,7 +313,7 @@ Agent-Native 執行時從 `.agents/skills/` 讀取 skills。 Claude 程式碼獨
   "id": "assets",
   "hosted": {
     "url": "https://assets.agent-native.com",
-    "mcpUrl": "https://assets.agent-native.com/_agent-native/mcp"
+    "mcpUrl": "https://assets.agent-native.com/mcp"
   },
   "mcp": { "serverName": "agent-native-assets" },
   "skills": [

package/docs/content/locales/zh-TW/template-assets.mdx

@@ -487,7 +487,7 @@ Codex、Claude 程式碼和 Claude 桌面程式碼應被視為連結輸出主機
 ### 開發者：分發應用技能
 
 資產應用技能的應用 ID為 `assets` 並託管 MCP URL
-`https://assets.agent-native.com/_agent-native/mcp`.
+`https://assets.agent-native.com/mcp`.
 
 ```bash
 # 最簡單的託管安裝：匯出的技能說明加上 MCP 連線器。

package/docs/content/locales/zh-TW/template-dispatch.mdx

@@ -123,7 +123,7 @@ Dispatch 是**工作區控制平面**。其他範本是域應用程式（郵件
   在不複製原始機密的情況下分派存取權限。應用程式特定來源
   設定保留在使用提供者的應用程式中。
 - **暴露一個 MCP 連線器。**新增
-  `https://dispatch.agent-native.com/_agent-native/mcp`，Claude、ChatGPT，
+  `https://dispatch.agent-native.com/mcp`，Claude、ChatGPT，
   Codex、Cursor 或其他 MCP 主機，然後選取要執行的工作區應用
   連線器可以從 Dispatch 的 **代理** 頁面進行存取。使用直接應用程式 URL
   僅當該主機應與一個應用隔離時。
@@ -304,7 +304,7 @@ _它的底層工作原理（對於開發人員）。_
   ]}
 />
 
-- **MCP 集線器模式。** Dispatch 仍然可以充當工作區的 [MCP hub](/docs/mcp-clients#hub)，因此工作區中的每個其他應用程式都會拉取相同的組織範圍 MCP 伺服器清單。另外，對於 Claude、ChatGPT 和其他應存取多個工作區應用的主機，Dispatch 自己的 `/_agent-native/mcp` 端點是推薦的外部 MCP 連線器。
+- **MCP 集線器模式。** Dispatch 仍然可以充當工作區的 [MCP hub](/docs/mcp-clients#hub)，因此工作區中的每個其他應用程式都會拉取相同的組織範圍 MCP 伺服器清單。另外，對於 Claude、ChatGPT 和其他應存取多個工作區應用的主機，Dispatch 自己的 `/mcp` 端點是推薦的外部 MCP 連線器。
 
 ## 夢想 {#dreams}
 

package/docs/content/locales/zh-TW/template-plan.mdx

@@ -110,7 +110,7 @@ npx @agent-native/core@latest skills add visual-plan
 
 如果您使用的是直接接受 MCP 連線器 URL 的基於聊天的主機
 （而不是 CLI 設定的用戶端），連線託管計畫連線器
-`https://plan.agent-native.com/_agent-native/mcp` — 請參閱 [MCP Clients](/docs/mcp-clients) 以了解特定於用戶端的設定。
+`https://plan.agent-native.com/mcp` — 請參閱 [MCP Clients](/docs/mcp-clients) 以了解特定於用戶端的設定。
 
 驗證是在設定時進行一次性瀏覽器登入 - 這是有意為之的
 是讓代理持續存在並共用其產生的計畫的原因。授權是什麼
@@ -249,7 +249,7 @@ vscode://builder.agent-native/open?url=<encoded-plan-url>
   跨設備或團隊審核）需要登入。Google 登入會在以下情況出現
   標準 Google OAuth 環境變數已設定。
 
-託管計畫連線器位於 `https://plan.agent-native.com/_agent-native/mcp`。
+託管計畫連線器位於 `https://plan.agent-native.com/mcp`。
 切勿將共用機密放入技能檔案中。
 
 ## 本機檔案隱私模式 {#local-files}
@@ -447,7 +447,7 @@ pnpm dev
 託管應用程式支援的技能使用：
 
 - 應用程式：`https://plan.agent-native.com`
-- MCP: `https://plan.agent-native.com/_agent-native/mcp`
+- MCP: `https://plan.agent-native.com/mcp`
 
 當您開發計畫本身、測試本機持久性或執行完全自託管的審核介面時，本機範本非常有用。
 

package/docs/content/mcp-clients.mdx

@@ -272,7 +272,32 @@ export default {
 ```
 
 Preset ids are `context7`, `sentry`, `notion`, `semgrep`, `linear`,
-`supabase`, `neon`, and `stripe`.
+`atlassian`, `supabase`, `neon`, and `stripe`.
+
+### Atlassian / Jira
+
+The Atlassian preset uses Atlassian Rovo MCP's OAuth 2.1 endpoint,
+`https://mcp.atlassian.com/v1/mcp/authv2`, and exposes Jira and Confluence
+tools. Creating Jira tickets requires the Atlassian permissions that cover
+Jira writes; the user still only sees the projects and content allowed by
+their Atlassian account.
+
+Atlassian organization admins can control whether an OAuth client is allowed
+to connect. Before connecting, an admin may need to add the app's actual HTTPS
+origin to the trusted-domain list under **Atlassian Administration → Rovo →
+Rovo MCP server → Domains**, and enable the required **Read**, **Write**, and
+**Search** permissions under **Permissions**. The domain must be the host where
+the agent-native app runs; do not copy `https://builder.io/**` to another
+deployment unless that is its actual origin. See Atlassian's [Rovo MCP setup
+guide](https://developer.atlassian.com/cloud/rovo-mcp/guides/getting-started/)
+and [admin controls](https://support.atlassian.com/security-and-access-policies/docs/control-atlassian-rovo-mcp-server-settings/).
+
+The catalog supplies the endpoint and setup guidance. The generic settings
+form stores the endpoint and optional encrypted headers; it does not replace
+Atlassian's interactive OAuth consent flow. Use an OAuth-capable MCP client or
+runtime when Atlassian requires interactive OAuth. If the provider or runtime
+supports a static bearer token, follow its approved secret-management path and
+never paste tokens into prompts or committed config.
 
 ### How to connect a remote MCP server
 
@@ -292,7 +317,7 @@ Two scopes are supported:
 
 Adds and removes hot-reload into the running MCP manager — no process restart, and no server restart. The new `mcp__<scope>-<name>__*` tools appear to the agent on the next message and are searchable via `tool-search`.
 
-HTTPS URLs are accepted everywhere; plain `http://` is only allowed for `localhost` during development. Optional auth goes in as a Bearer token that's sent via `Authorization: Bearer …` on every request.
+HTTPS URLs are accepted everywhere; plain `http://` is only allowed for `localhost` during development. Optional auth goes in as a Bearer token that's sent via `Authorization: Bearer …` on every request. OAuth-only providers, including Atlassian Rovo MCP, require the provider's OAuth flow instead of a static header.
 
 Under the hood these servers are persisted in the framework's `settings` table under the key `u:<email>:mcp-servers-remote` (Personal) or `o:<orgId>:mcp-servers-remote` (Team) and merged with `mcp.config.json` on startup.
 
@@ -355,7 +380,9 @@ pull its org-scope MCP servers automatically. Dispatch is the conventional hub
   <div class="diagram-panel center" data-rough>
     <span class="diagram-pill accent">Dispatch hub</span
     ><small class="diagram-muted">org-scope MCP servers</small
-    ><small class="diagram-muted"><code>GET /mcp/hub/servers</code></small>
+    ><small class="diagram-muted"
+      ><code>GET /_agent-native/mcp/hub/servers</code></small
+    >
   </div>
   <div class="diagram-col arrows">
     <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
@@ -469,7 +496,7 @@ Reports which configured servers connected, the total live tool count, the merge
 
 Individual MCP server failures never take down the agent:
 
-- A misconfigured `command` → the server is skipped, its error appears in `/mcp/status` under `errors.<server-id>`, and every other server continues to work.
+- A misconfigured `command` → the server is skipped, its error appears in `/_agent-native/mcp/status` under `errors.<server-id>`, and every other server continues to work.
 - The MCP SDK is missing from `node_modules` → all MCP functionality is skipped with a warning; agent chat keeps working with zero MCP tools.
 - Running in an edge runtime → MCP client is a no-op.
 

package/docs/content/mcp-protocol.mdx

@@ -23,7 +23,7 @@ MCP is the standard protocol for connecting AI tools to external capabilities. W
 
 Key concepts:
 
-- **Auto-mounted** — every app gets `/_agent-native/mcp` for free, no setup required
+- **Auto-mounted** — every app gets `/mcp` for free, no setup required
 - **Streamable HTTP** — uses the modern MCP transport over standard HTTP (POST + SSE)
 - **Same actions** — the exact same action registry that powers agent chat and A2A
 - **`ask-agent` tool** — a meta-tool that delegates to the full agent loop for complex tasks
@@ -42,7 +42,7 @@ Key concepts:
   </div>
   <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
   <div class="diagram-panel">
-    <span class="diagram-pill accent">POST /_agent-native/mcp</span
+    <span class="diagram-pill accent">POST /mcp</span
     ><small class="diagram-muted">Streamable HTTP</small
     ><small class="diagram-muted"
       >initialize &rarr; tools/list &rarr; tools/call</small
@@ -95,7 +95,7 @@ Both protocols are auto-mounted. Use whichever fits your use case:
 | **Best for**       | External tools calling your app                                          | Agent-to-agent communication                 |
 | **Protocol**       | MCP Streamable HTTP                                                      | JSON-RPC 2.0                                 |
 | **Tool discovery** | `tools/list`                                                             | Agent card at `/.well-known/agent-card.json` |
-| **Endpoint**       | `/_agent-native/mcp`                                                     | `/_agent-native/a2a`                         |
+| **Endpoint**       | `/mcp`                                                                   | `/_agent-native/a2a`                         |
 | **Supported by**   | Claude, ChatGPT, Claude Code, Cursor, Codex, Cowork, and other MCP hosts | Other agent-native apps                      |
 | **Execution**      | Direct tool calls (no extra LLM)                                         | Full agent loop (LLM reasoning)              |
 
@@ -106,7 +106,7 @@ You can also use the `ask-agent` MCP tool to get the best of both worlds — cal
 For the recommended one-command setup, use [External Agents](/docs/external-agents). If you are hand-writing MCP config for an OAuth-capable host, add your app as a remote MCP server with no static headers:
 
 ```bash
-claude mcp add --transport http mail https://mail.example.com/_agent-native/mcp
+claude mcp add --transport http mail https://mail.example.com/mcp
 ```
 
 Or write the entry by hand in `.mcp.json` (project scope) or `~/.claude.json` (user scope):
@@ -117,7 +117,7 @@ Or write the entry by hand in `.mcp.json` (project scope) or `~/.claude.json` (u
   "mcpServers": {
     "mail": {
       "type": "http",
-      "url": "https://mail.example.com/_agent-native/mcp",
+      "url": "https://mail.example.com/mcp",
     },
   },
 }
@@ -136,12 +136,12 @@ Claude Code calls: draft-email(to: "john@example.com", subject: "Q3 Report", bod
 Any MCP host that supports Streamable HTTP transport can connect. The endpoint is:
 
 ```
-POST https://your-app.example.com/_agent-native/mcp
+POST https://your-app.example.com/mcp
 ```
 
 The server supports the standard MCP handshake: `initialize` → `initialized` → `tools/list` → `tools/call`.
 
-<Endpoint id="doc-block-86ic5g" title="MCP endpoint" summary="The auto-mounted Streamable HTTP endpoint every agent-native app exposes." method="POST" path="/_agent-native/mcp" auth="Standard remote MCP OAuth (Bearer access token), connect-minted JWT, or static ACCESS_TOKEN/ACCESS_TOKENS" params={[
+<Endpoint id="doc-block-86ic5g" title="MCP endpoint" summary="The auto-mounted Streamable HTTP endpoint every agent-native app exposes." method="POST" path="/mcp" auth="Standard remote MCP OAuth (Bearer access token), connect-minted JWT, or static ACCESS_TOKEN/ACCESS_TOKENS" params={[
   {
     "name": "Authorization",
     "in": "header",
@@ -211,18 +211,38 @@ When `mcpApp` is present, the tool entry also includes `_meta.ui.resourceUri`, `
 
 In addition to individual action tools, every MCP server includes an `ask-agent` meta-tool. This sends a natural-language message to the app's AI agent and returns the response.
 
+Hosted MCP requests use a bounded inline wait so a long agent loop does not
+keep one `tools/call` open until a client or gateway timeout. The optional
+`async` argument starts the durable task and returns immediately; without it,
+the server waits briefly for a fast completion and then returns a task handle
+when more work remains. The hosted wait is capped at 25 seconds.
+
 Use `ask-agent` for complex tasks that benefit from the agent's reasoning and context:
 
 ```json
 {
   "name": "ask-agent",
   "arguments": {
-    "message": "Draft a follow-up email to the Q3 planning thread with John, summarizing the action items we discussed"
+    "message": "Draft a follow-up email to the Q3 planning thread with John, summarizing the action items we discussed",
+    "async": true
+  }
+}
+```
+
+The agent runs the same loop as the interactive chat — it can call multiple tools, reason about context, and produce a thoughtful response. A task that is not finished returns JSON containing `taskId`, `status`, `pollAfterMs`, and:
+
+```json
+{
+  "poll": {
+    "tool": "ask_app_status",
+    "arguments": { "app": "mail", "taskId": "task_123" }
   }
 }
 ```
 
-The agent runs the same loop as the interactive chat — it can call multiple tools, reason about context, and produce a thoughtful response.
+Call `ask_app_status` with those arguments until the task reaches a terminal
+state. Dispatch's app-owned `ask_app` uses the same durable task and status
+contract, with the selected-app grant checked on both submission and polling.
 
 ## Authentication {#authentication}
 
@@ -240,7 +260,7 @@ The MCP endpoint supports standard remote MCP OAuth plus the existing bearer-tok
 For OAuth-capable MCP hosts, configure the remote server URL with no static headers:
 
 ```bash
-claude mcp add --transport http agent-native https://dispatch.agent-native.com/_agent-native/mcp
+claude mcp add --transport http agent-native https://dispatch.agent-native.com/mcp
 ```
 
 The first unauthenticated MCP request receives:
@@ -256,9 +276,9 @@ Discovery endpoints:
 | ----------------------------------------- | ------------------------------------------- |
 | `/.well-known/oauth-protected-resource`   | RFC 9728 protected-resource metadata        |
 | `/.well-known/oauth-authorization-server` | OAuth authorization server metadata         |
-| `/_agent-native/mcp/oauth/register`       | Dynamic public-client registration          |
-| `/_agent-native/mcp/oauth/authorize`      | Browser authorization + consent             |
-| `/_agent-native/mcp/oauth/token`          | Authorization-code and refresh-token grants |
+| `/mcp/oauth/register`                     | Dynamic public-client registration          |
+| `/mcp/oauth/authorize`                    | Browser authorization + consent             |
+| `/mcp/oauth/token`                        | Authorization-code and refresh-token grants |
 
 <Diagram id="doc-block-79kjly" title="OAuth discovery flow" summary={"A 401 kicks off discovery, registration, and a PKCE authorize → token exchange. The Bearer token is audience-bound and scoped."}>
 
@@ -358,7 +378,7 @@ export default defineNitroPlugin(async (nitro) => {
 You have a deployed analytics app at `analytics.example.com`. From Claude Code:
 
 ```bash
-claude mcp add --transport http analytics https://analytics.example.com/_agent-native/mcp
+claude mcp add --transport http analytics https://analytics.example.com/mcp
 ```
 
 Or add it by hand in `.mcp.json`:
@@ -369,7 +389,7 @@ Or add it by hand in `.mcp.json`:
   "mcpServers": {
     "analytics": {
       "type": "http",
-      "url": "https://analytics.example.com/_agent-native/mcp",
+      "url": "https://analytics.example.com/mcp",
     },
   },
 }

package/docs/content/plan-plugin.mdx

@@ -12,7 +12,7 @@ The Agent-Native **Plan** app ships as one installable bundle. A single install
 One install gives you:
 
 - **Three skills** — `/visual-plan` (the canonical entry point), `/visual-recap`, and `/visualize-repo`.
-- **The Plan MCP connector** — registered against the hosted app at `https://plan.agent-native.com` (MCP endpoint `https://plan.agent-native.com/_agent-native/mcp`, server name `plan`).
+- **The Plan MCP connector** — registered against the hosted app at `https://plan.agent-native.com` (MCP endpoint `https://plan.agent-native.com/mcp`, server name `plan`).
 
 <Diagram id="doc-block-i1sn3n" title="Three routes, one bundle" summary="The universal CLI, Claude Code plugin, and Codex plugin all install the same Plan skills plus the hosted Plan connector.">
 
@@ -43,7 +43,7 @@ One install gives you:
   <div class="diagram-arrow diagram-muted" aria-hidden="true">&rarr;</div>
   <div class="diagram-box">
     Plan MCP connector<br /><small class="diagram-muted"
-      >plan.agent-native.com/_agent-native/mcp</small
+      >plan.agent-native.com/mcp</small
     >
   </div>
 </div>
@@ -251,7 +251,7 @@ codex plugin add agent-native-visual-plans@agent-native-apps
 codex mcp login plan   # OAuth in the browser
 ```
 
-After install, **start a new Codex thread** so the skills and MCP tools load into the session. The plugin ships a URL-only connector (`[mcp_servers.plan]` → `https://plan.agent-native.com/_agent-native/mcp`); `codex mcp login plan` runs the OAuth flow. The universal CLI route above also works for Codex (`npx @agent-native/core@latest skills add visual-plan --client codex`) if you prefer one command that installs and authenticates together, or when you want local-files or self-hosted mode.
+After install, **start a new Codex thread** so the skills and MCP tools load into the session. The plugin ships a URL-only connector (`[mcp_servers.plan]` → `https://plan.agent-native.com/mcp`); `codex mcp login plan` runs the OAuth flow. The universal CLI route above also works for Codex (`npx @agent-native/core@latest skills add visual-plan --client codex`) if you prefer one command that installs and authenticates together, or when you want local-files or self-hosted mode.
 
 <Callout tone="info">
 

package/docs/content/server.mdx

@@ -269,7 +269,7 @@ The framework mounts its own routes under `/_agent-native/`. Treat that namespac
 | `/_agent-native/extensions/*`    | Runtime extensions and extension proxy (legacy alias: `/_agent-native/tools/*`) |
 | `/_agent-native/integrations/*`  | Messaging/webhook integrations                                                  |
 | `/_agent-native/a2a`             | Agent-to-agent JSON-RPC                                                         |
-| `/_agent-native/mcp`             | MCP endpoint                                                                    |
+| `/mcp`                           | MCP endpoint                                                                    |
 | `/_agent-native/onboarding/*`    | Setup checklist                                                                 |
 | `/_agent-native/observability/*` | Traces, feedback, evals, experiments                                            |
 | `/_agent-native/file-upload`     | File upload provider endpoint                                                   |
@@ -465,4 +465,4 @@ const handler = createProductionAgentHandler({
 - [**Database**](/docs/database) — the `getDb()`/`schema` pattern custom routes and actions both import
 - [**Security**](/docs/security#access-guards) — `accessFilter`/`assertAccess` and the full data-scoping model
 - [**Messaging**](/docs/messaging) — the canonical inbound-webhook integration queue pattern
-- [**MCP Protocol**](/docs/mcp-protocol) — the `/_agent-native/mcp` endpoint this server mounts automatically
+- [**MCP Protocol**](/docs/mcp-protocol) — the `/mcp` endpoint this server mounts automatically

package/docs/content/skills-guide.mdx

@@ -317,7 +317,7 @@ Each app-backed skill starts with `agent-native.app-skill.json` at the app root:
   "id": "assets",
   "hosted": {
     "url": "https://assets.agent-native.com",
-    "mcpUrl": "https://assets.agent-native.com/_agent-native/mcp"
+    "mcpUrl": "https://assets.agent-native.com/mcp"
   },
   "mcp": { "serverName": "agent-native-assets" },
   "skills": [

package/docs/content/template-assets.mdx

@@ -628,7 +628,7 @@ human picker UI.
 ### Developer: distribute the app skill
 
 The Assets app skill has app id `assets` and hosted MCP URL
-`https://assets.agent-native.com/_agent-native/mcp`.
+`https://assets.agent-native.com/mcp`.
 
 ```bash
 # Easiest hosted install: exported skill instructions plus MCP connector.

package/docs/content/template-dispatch.mdx

@@ -123,7 +123,7 @@ Day-to-day, Dispatch is the place admins and ops folks open to keep the workspac
   Dispatch access without copying raw secrets. App-specific source
   configuration stays in the app that uses the provider.
 - **Expose one MCP connector.** Add
-  `https://dispatch.agent-native.com/_agent-native/mcp` in Claude, ChatGPT,
+  `https://dispatch.agent-native.com/mcp` in Claude, ChatGPT,
   Codex, Cursor, or another MCP host, then choose which workspace apps the
   connector can reach from Dispatch's **Agents** page. Use a direct app URL
   only when that host should be isolated to one app.
@@ -304,7 +304,7 @@ _How it works under the hood (for developers)._
   ]}
 />
 
-- **MCP hub mode.** Dispatch can still act as the workspace's [MCP hub](/docs/mcp-clients#hub) so every other app in the workspace pulls the same org-scope MCP server list. Separately, Dispatch's own `/_agent-native/mcp` endpoint is the recommended external MCP connector for Claude, ChatGPT, and other hosts that should reach multiple workspace apps.
+- **MCP hub mode.** Dispatch can still act as the workspace's [MCP hub](/docs/mcp-clients#hub) so every other app in the workspace pulls the same org-scope MCP server list. Separately, Dispatch's own `/mcp` endpoint is the recommended external MCP connector for Claude, ChatGPT, and other hosts that should reach multiple workspace apps.
 
 ## Dreams {#dreams}
 

package/docs/content/template-plan.mdx

@@ -124,7 +124,7 @@ The command installs three commands: `/visual-plan`, `/visual-recap`, and
 
 If you are using a chat-based host that accepts MCP connector URLs directly
 (rather than a CLI-configured client), connect the hosted Plans connector at
-`https://plan.agent-native.com/_agent-native/mcp` — see [MCP Clients](/docs/mcp-clients) for client-specific setup.
+`https://plan.agent-native.com/mcp` — see [MCP Clients](/docs/mcp-clients) for client-specific setup.
 
 Authentication is a one-time browser sign-in at setup — this is intended, and it
 is what lets the agent persist and share the plans it generates. What the auth
@@ -267,7 +267,7 @@ Sharing and commenting are the workflows that need an account:
   cross-device or team review) requires signing in. Google sign-in appears when
   the standard Google OAuth env vars are configured.
 
-The hosted Plans connector lives at `https://plan.agent-native.com/_agent-native/mcp`.
+The hosted Plans connector lives at `https://plan.agent-native.com/mcp`.
 Never put shared secrets in skill files.
 
 ## Local-files privacy mode {#local-files}
@@ -475,7 +475,7 @@ pnpm dev
 The hosted app-backed skill uses:
 
 - App: `https://plan.agent-native.com`
-- MCP: `https://plan.agent-native.com/_agent-native/mcp`
+- MCP: `https://plan.agent-native.com/mcp`
 
 The local template is useful when you are developing Plans itself, testing local persistence, or running a fully self-hosted review surface.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@agent-native/core",
-  "version": "0.98.16",
+  "version": "0.99.0",
   "description": "Framework for agent-native application development — where AI agents and UI share SQL state, actions, and context",
   "homepage": "https://github.com/BuilderIO/agent-native#readme",
   "bugs": {