Update from code changes: document agent scheduled delivery tool

guides/ai-agents/content-tools.mdx

@@ -31,6 +31,18 @@ When content editing is enabled, your agent can:
 - Rename content or update its description
 - Move charts and dashboards to another space
 
+**Set up scheduled deliveries:**
+
+- Create a [scheduled delivery](/guides/how-to-create-scheduled-deliveries) for an existing chart or dashboard, targeting Slack channels and/or email recipients
+- Choose the format (rendered image or CSV), cron schedule, and timezone
+- Optionally attach an AI-written delivery message that is regenerated from the delivered data on every send
+
+<Warning>
+  Scheduled deliveries created by an agent go live as soon as they are created. When the desired schedule is unclear, ask the agent to create the delivery paused so you can review it in **Scheduled deliveries** before enabling it.
+</Warning>
+
+The agent proposes the full configuration — name, schedule, destinations, format, and any AI-augmented message — and waits for your explicit confirmation before creating the delivery. For example: _"Every Monday at 9am, email the ecom weekly-revenue chart as a CSV to analytics@example.com, with an AI summary of the biggest week-over-week changes."_
+
 ## Spaces
 
 Content created by an agent is saved in a Lightdash space, just like content created from the Explore page or dashboard editor. Tell the agent which space to use when you want the content saved somewhere specific. If you do not name a space, the agent can choose the best match from the spaces it has access to.
@@ -49,6 +61,8 @@ Content editing is available only when all of these are true:
 
 Turning the setting on does not give viewers or interactive viewers new permissions. If they ask the agent to create or edit saved content, the agent will not have those tools available.
 
+Scheduled deliveries the agent creates are subject to the requesting user's own delivery permissions — the agent can only set up deliveries that user could set up in the Lightdash UI.
+
 <Info>
 **In the Lightdash app:** the logged-in user's permissions are used for every request.
 

references/integrations/lightdash-mcp.mdx

@@ -15,7 +15,7 @@ With MCP, your AI assistant becomes a data analyst that can:
 - Find relevant metrics and dimensions
 - Run queries and generate visualizations
 - Discover existing charts and dashboards, including verified content
-- Create and edit charts and dashboards using content-as-code
+- Create and edit charts and dashboards using content-as-code, and schedule deliveries for them
 - Leverage your AI agents' domain expertise and verified answers
 - Switch between different projects seamlessly
 - Respect your data governance and access controls
@@ -420,9 +420,14 @@ MCP can read, create, and edit Lightdash charts and dashboards using the same [c
 - **Read content** (`read_content`) - Fetch a chart or dashboard as JSON by slug. Call this before editing so the agent can see the current state.
 - **Edit content** (`edit_content`) - Apply an [RFC 6902 JSON Patch](https://datatracker.ietf.org/doc/html/rfc6902) to an existing chart or dashboard, then validate and persist. Use this for surgical changes (e.g. rename a field, add a filter, swap a chart color) without rewriting the whole object.
 - **Create content** (`create_content`) - Create a new chart or dashboard from a full chart-as-code or dashboard-as-code object. Returns the persisted slug and URL.
+- **Create scheduled delivery** (`create_scheduled_delivery`) - Create a [scheduled delivery](/guides/how-to-create-scheduled-deliveries) for an existing chart or dashboard, sending it to Slack channels and/or email recipients on a cron schedule. Supports image or CSV format and an optional AI-written message that is regenerated from the delivered data on every send. The delivery is created through the same services as the Lightdash UI, so it respects the requesting user's scheduled delivery permissions.
 
 These tools reuse the same permissions, validation, and project context as the [Lightdash CLI](/guides/cli/how-to-install-the-lightdash-cli) `download` and `upload` commands, so the user driving the MCP session needs the same access required to manage that content in Lightdash.
 
+<Warning>
+  Deliveries created via `create_scheduled_delivery` are live the moment they are created. Ask the assistant to confirm the full configuration — name, cron, timezone, destinations, format, and any AI-augmented message — before calling the tool, and to create it paused when the desired schedule is unclear.
+</Warning>
+
 <Info>
   **Admin kill-switch.** Organization admins can disable content writes across all MCP clients from **Settings → Ask AI → General** by turning off **Allow content changes via MCP**. When this is off, `create_content` and `edit_content` are not registered for any MCP client in the organization — reading content over MCP is unaffected, and per-user permissions still apply when it's on. The toggle is **on by default**.
 </Info>
@@ -719,7 +724,7 @@ A: Yes, each team member can set up their own MCP connection with their individu
 
 **Q: Can MCP modify my data or dashboards?**
 
-A: MCP can create and edit Lightdash charts and dashboards via the [content-as-code tools](#editing-content) when your user account has the required permissions. MCP cannot modify your underlying warehouse data — query execution is read-only (metric queries and SQL `SELECT` only). All write operations respect your existing Lightdash permissions and project access controls.
+A: MCP can create and edit Lightdash charts and dashboards, and create scheduled deliveries for them, via the [content-as-code tools](#editing-content) when your user account has the required permissions. MCP cannot modify your underlying warehouse data — query execution is read-only (metric queries and SQL `SELECT` only). All write operations respect your existing Lightdash permissions and project access controls.
 
 **Q: Claude returns data as text but no visual chart is displayed. What's wrong?**