Merge branch 'main' into discord-bot

Author: ethanpalm

ai-native.mdx

@@ -16,7 +16,7 @@ In addition to reading individual pages, users can chat with the [assistant](/ai
 
 The [agent](/ai/agent) helps you write and maintain documentation. It creates pull requests with proposed changes based on your prompts, pull requests, and Slack threads. Add the agent to your Slack workspace so that anyone on your team can help maintain your documentation by chatting with the agent. Or embed the agent into custom apps via the [API](/api-reference/agent/create-agent-job).
 
-[Autopilot](/ai/autopilot) monitors connected repositories and proactively suggests documentation updates when it identifies user-facing changes.
+You can configure the agent to monitor connected repositories and proactively [suggest](/ai/suggestions) documentation updates when it identifies user-facing changes.
 
 Configure popular tools like [Cursor](/guides/cursor), [Claude Code](/guides/claude-code), and [Windsurf](/guides/windsurf) to reference the Mintlify schema, your style guide, and best practices.
 
@@ -41,7 +41,7 @@ Select any of the following cards for more information.
   <Card title="Agent" icon="pen-line" href="/ai/agent">
     Add the agent to your Slack workspace or embed it into custom apps to have it help write and update your documentation.
   </Card>
-    <Card title="Autopilot" icon="plane-takeoff" href="/ai/autopilot">
+    <Card title="Suggestions" icon="message-circle-plus" href="/ai/suggestions">
     Monitor Git repositories for changes and receive suggested documentation updates.
   </Card>
   <Card title="Contextual menu" icon="sparkles" href="/ai/contextual-menu">

ai/assistant.mdx

@@ -12,7 +12,7 @@ keywords: ["chat", "RAG", "user support"]
 
 The assistant answers questions about your documentation through natural language queries. It is embedded directly in your documentation site, so users can find answers quickly and succeed with your product.
 
-The assistant uses agentic RAG (retrieval-augmented generation) with tool calling powered by Claude Sonnet 4.5. When users ask questions, the assistant:
+The assistant uses agentic RAG (retrieval-augmented generation) with tool calling powered by Claude Opus 4.5. When users ask questions, the assistant:
 
 * **Searches and retrieves** relevant content from your documentation to provide accurate answers.
 * **Cites sources** and provides navigable links to take users directly to referenced pages.

ai/autopilot.mdx

@@ -8,19 +8,19 @@ import { PreviewButton } from "/snippets/previewbutton.jsx"
 
 ## About MCP servers
 
-The Model Context Protocol (MCP) is an open protocol that creates standardized connections between AI applications and external services, like documentation. Mintlify generates an MCP server from your documentation and OpenAPI specifications, preparing your content for the broader AI ecosystem where any MCP client (like Claude, Cursor, Goose, and others) can connect to your documentation and APIs.
+The Model Context Protocol (MCP) is an open protocol that creates standardized connections between AI applications and external services, like documentation. Mintlify generates an MCP server from your documentation, preparing your content for the broader AI ecosystem where any MCP client (like Claude, Cursor, Goose, and others) can connect to your documentation.
 
-Your MCP server exposes tools for AI applications to search your documentation and interact with your APIs.
+Your MCP server exposes a search tool for AI applications to query your documentation.
 
 ### How MCP servers work
 
-When an MCP server is connected to an AI tool, the LLM can decide to use your documentation and API tools during response generation.
+When an MCP server is connected to an AI tool, the LLM can decide to use your documentation search tool during response generation.
 
-- The LLM can proactively search your documentation or call your API endpoints while generating a response, not just when explicitly asked.
-- The LLM determines when to use tools based on the context of the conversation and the relevance of your documentation and APIs.
-- Each tool call happens during the generation process, allowing the LLM to incorporate real-time information from your documentation and APIs into its response.
+- The LLM can proactively search your documentation while generating a response, not just when explicitly asked.
+- The LLM determines when to use the search tool based on the context of the conversation and the relevance of your documentation.
+- Each tool call happens during the generation process, allowing the LLM to incorporate real-time information from your documentation into its response.
 
-For example, if a user asks a coding question and the LLM determines that your API documentation is relevant, it can search your API documentation and include that information in the response without the user explicitly asking about your documentation.
+For example, if a user asks a coding question and the LLM determines that your documentation is relevant, it can search your documentation and include that information in the response without the user explicitly asking about your documentation.
 
 ## Accessing your MCP server
 
@@ -34,96 +34,13 @@ You can see and copy your MCP server URL in your [dashboard](https://dashboard.m
 
 The `/mcp` path is reserved for hosted MCP servers and cannot be used for other navigation elements.
 
-## Configuring your MCP server
-
-All MCP servers include the `search` tool by default, which allows users to query information from your docs in other tools.
-
-If you have a [Pro or Custom plan](https://mintlify.com/pricing?ref=mcp), you can expose endpoints from your OpenAPI specification as MCP tools.
-
-To expose endpoints as MCP tools, use the `mcp` object within the `x-mint` extension at either the file or endpoint level. For example, the Mintlify MCP server includes tools to create assistant chats, get status updates, and trigger updates.
-
-MCP servers follow a security-first approach where API endpoints are not exposed by default. You must explicitly enable endpoints to make them available as MCP tools. Only expose endpoints that are safe for public access through AI tools.
-
-<ResponseField name="mcp" type="object">
-  The MCP configuration for the endpoint.
-
-  <Expandable title="MCP">
-    <ResponseField name="enabled" type="boolean">
-      Whether to expose the endpoint as an MCP tool. Takes precedence over the file-level configuration.
-    </ResponseField>
-    <ResponseField name="name" type="string">
-      The name of the MCP tool.
-    </ResponseField>
-    <ResponseField name="description" type="string">
-      The description of the MCP tool.
-    </ResponseField>
-  </Expandable>
-</ResponseField>
-
-### File-level configuration
-
-Enable MCP for all endpoints by default in an OpenAPI specification file and selectively exclude endpoints:
-
-```json
-{
-  "openapi": "3.1.0",
-  "x-mint": {
-    "mcp": {
-      "enabled": true
-    }
-  },
-  // ...
-  "paths": {
-    "/api/v1/users": {
-      "get": {
-        "x-mint": {
-          "mcp": {
-            "enabled": false // Disables MCP for this endpoint
-          }
-        },
-        // ...
-      }
-    }
-  }
-}
-```
-
-### Endpoint-level configuration
-
-Enable MCP for specific endpoints:
-
-```json
-{
-  "paths": {
-    "/api/v1/users": {
-      "get": {
-        "x-mint": {
-          "mcp": {
-            "enabled": true,
-            "name": "get-users",
-            "description": "Get a list of users"
-          },
-          // ...
-        }
-      }
-    },
-    "/api/v1/delete": {
-      "delete": {
-        // No `x-mint: mcp` so this endpoint is not exposed as an MCP tool
-        // ...
-      }
-    }
-  }
-}
-```
-
 ## Using your MCP server
 
 Your users must connect your MCP server to their preferred AI tools.
 
 1. Make your MCP server URL publicly available.
 2. Users copy your MCP server URL and add it to their tools.
-3. Users access your documentation and API endpoints through their tools.
+3. Users access your documentation through their tools.
 
 These are some of the ways you can help your users connect to your MCP server:
 
@@ -229,7 +146,7 @@ See the [Claude Code documentation](https://docs.anthropic.com/en/docs/claude-co
 
 ### Example: Connecting to the Mintlify MCP server
 
-Connect to the Mintlify MCP server to interact with the Mintlify API and search our documentation. This will give you more accurate answers about how to use Mintlify in your local environment and demonstrates how you can help your users connect to your MCP server.
+Connect to the Mintlify MCP server to search our documentation. This will give you more accurate answers about how to use Mintlify in your local environment and demonstrates how you can help your users connect to your MCP server.
 
 <Tabs>
 <Tab title="Contextual menu">
@@ -327,11 +244,7 @@ See the [VS Code documentation](https://code.visualstudio.com/docs/copilot/chat/
 </Tab>
 </Tabs>
 
-## Authentication
-
-When you enable an API endpoint for MCP, the server includes the authentication requirements defined in your OpenAPI `securitySchemes` and `securityRequirement`. Any keys are handled directly by the tool and not stored or processed by Mintlify.
 
-If a user asks their AI tool to call a protected endpoint, the tool will request the necessary authentication credentials from the user at that moment.
 
 ## Monitoring your MCP server
 
@@ -342,29 +255,4 @@ You can view all available MCP tools in the **Available tools** section of the [
   <img src="/images/mcp/mcp-server-page-dark.png" alt="MCP dashboard with Available tools section emphasized" className="hidden dark:block" />
 </Frame>
 
-## Troubleshooting
-
-<AccordionGroup>
-  <Accordion title="MCP server only shows search tool">
-    If your MCP server only exposes the search tool despite having an OpenAPI specification:
-
-    1. Verify your OpenAPI specification is valid and accessible.
-    2. Ensure you've explicitly enabled MCP for specific endpoints using `x-mint.mcp.enabled: true`.
-    3. Check your deployment logs for OpenAPI processing errors.
-
-    If OpenAPI processing fails, the server continues with just the search tool to maintain functionality.
-  </Accordion>
-  <Accordion title="Authentication issues">
-    If users report authentication problems:
-
-    1. Check that your OpenAPI specification includes proper `securitySchemes` definitions.
-    2. Confirm that enabled endpoints work with the specified authentication methods.
-  </Accordion>
-  <Accordion title="Tool descriptions missing or unclear">
-    If AI tools aren't using your API endpoints effectively:
 
-    1. Add detailed `summary` and `description` fields to your endpoints.
-    2. Ensure parameter names and descriptions are self-explanatory.
-    3. Use the MCP dashboard to verify how your endpoints appear as tools.
-  </Accordion>
-</AccordionGroup>

ai/model-context-protocol.mdx

@@ -1,27 +1,45 @@
 ---
 title: "Slack app"
-description: "Add a bot that searches your docs to answers questions in your Slack workspace."
-keywords: ["Slack bot", "workspace", "questions"]
+description: "Add a bot to your Slack workspace that answers questions based on your documentation."
+keywords: ["bot", "workspace", "Q&A", "Slack"]
 ---
 
 <Info>
-  The Slack app is available for [Pro and Custom plans](https://mintlify.com/pricing?ref=slack-app).
+  The Slack app is available for [Pro and Custom plans](https://mintlify.com/pricing?ref=slack-app) with access to the assistant.
 </Info>
 
-The Slack app adds a bot to your Slack workspace that can search your documentation and answer users' questions. The bot responds to direct messages, @mentions, and to any questions in a channel specifically named `#ask-ai`. The bot's name is `@yourprojectname-assistant`. So if your project name is Mintlify, the bot's name is `@mintlify-assistant`.
+The Slack app adds a bot to your workspace that supports your community with real-time answers. The bot uses the Mintlify assistant to search your docs and provide accurate, cited responses, so it is always up-to-date.
 
-The Slack app can incur costs: either using your AI assistant credits or incurring overages.
+The bot responds to `@` mentions and to every message in channels named `#ask-ai`.
+
+Each message sent by the bot counts toward your assistant message usage.
 
 ## Set up the Slack app
 
 <Note>
   If your Slack Workspace Owner requires admin approval to install apps, ask them to approve the Mintlify Slack app before you add it.
 </Note>
 
-1. Navigate to the [Add-ons](https://dashboard.mintlify.com/products/addons) page of your dashboard.
-2. Select **Connect** in the Slack Integration card.
-3. Follow the Slack prompts to add the app to your workspace.
-4. Test that the bot is working and responds when you:
-  - Send a direct message to the bot.
-  - Mention the bot in a channel.
-  - Create an `#ask-ai` channel, add the bot, and ask a question.
+1. Navigate to the [Integrations](https://dashboard.mintlify.com/products/assistant/settings/integrations) tab of the **Assistant Configurations** page in your dashboard.
+1. In the Slack card, click **Connect**. This opens Slack.
+  <Frame>
+    <img src="/images/assistant/slack-connect-light.png" alt="The Connect button in the Slack card in light mode." className="block dark:hidden" />
+    <img src="/images/assistant/slack-connect-dark.png" alt="The Connect button in the Slack card in dark mode." className="hidden dark:block" />
+  </Frame>
+1. Follow the Slack prompts to add the app to your workspace.
+1. Mention the bot to add it to a channel. The bot's default name is `@mintlify-assistant`.
+
+### Customize the bot's name
+
+1. In Slack, select the Mintlify app in the **Apps** menu.
+1. Click **About**.
+1. Click **Configuration**. This opens the app configuration page in a web browser.
+1. In the **Bot User** section, edit the bot name.
+
+## Create an `#ask-ai` channel
+
+To help your users quickly get answers to their questions, create a channel named `#ask-ai`. The bot will respond to every message in that channel. See [Create a channel](https://slack.com/help/articles/201402297-Create-a-channel) in the Slack Help Center for more information.
+
+## Manage the Slack app
+
+After you add the app to your workspace, you can manage or remove the app from the [Integrations](https://dashboard.mintlify.com/products/assistant/settings/integrations) tab.