Fix style consistency issues across docs

ai/model-context-protocol.mdx

@@ -8,7 +8,7 @@
 
 ## 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, preparing your content for the broader AI ecosystem where any MCP client like Claude, Cursor, Goose, ChatGPT, and others can connect to your documentation.
+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. Any MCP client like Claude, Cursor, Goose, or ChatGPT can connect to your documentation.
 
 Your MCP server exposes tools for AI applications to search your documentation and retrieve full page content. Your users must connect your MCP server to their tools.
 
@@ -18,7 +18,7 @@
 
 ### How MCP servers work
 
-When an AI application connects to your documentation MCP server, it can search your documentation and retrieve full page content directly in response to a user's prompt instead of relying on information from its training data or making a generic web search. Your MCP server provides access to all indexed content on your documentation site.
+When an AI application connects to your documentation MCP server, it can search your documentation and retrieve full page content directly in response to a user's prompt. This avoids relying on information from training data or generic web searches. Your MCP server provides access to all indexed content on your documentation site.
 
 - AI applications can proactively search your documentation while generating a response even if not explicitly asked to search your documentation for an answer.
 - AI applications determine when to use the available tools based on the context of the conversation and the relevance of your documentation.
@@ -48,7 +48,7 @@
 The MCP search tool supports optional parameters that AI applications use to control and refine search results.
 
 - **`pageSize`**: Number of results to return, between 1 and 50. Defaults to 10.
 - **`scoreThreshold`**: Minimum relevance score between 0 and 1. Only returns results at or above this threshold. Use this to filter out low-relevance matches.
 - **`version`**: Filter results to a specific documentation version. For example, `'v0.7'`. Only returns content tagged with the specified version or content available across all versions.
 - **`language`**: Filter results to a specific language code. For example, `'en'`, `'zh'`, or `'es'`. Only returns content in the specified language or content available across all languages.
 

assistant/use.mdx

@@ -4,7 +4,7 @@ description: "Open the assistant with keyboard shortcuts, highlighted text, code
 keywords: ["assistant", "keyboard shortcut", "file attachments", "local preview", "URL parameters"]
 ---
 
-Users have multiple ways to start a conversation with the assistant. Each method opens a chat panel on the right side of your docs. Users can ask any question and the assistant searches your documentation for an answer. If the assistant cannot retrieve relevant information, the assistant responds that it cannot answer the question.
+Users have multiple ways to start a conversation with the assistant. Each method opens a chat panel on the right side of your docs. Users can ask any question and the assistant searches your documentation for an answer. If the assistant cannot retrieve relevant information, it responds that it cannot answer the question.
 
 ## Use the assistant in local preview
 

editor/share-a-preview.mdx

@@ -6,16 +6,16 @@
 
 ## Preview deployments
 
 Every time you save changes to a feature branch, Mintlify builds a preview deployment — a temporary URL where your changes are rendered exactly as they'll look when published. Use it to review your work or collect feedback before merging.
 
 ### Access your preview
 
 1. Click **Publish** in the editor toolbar.
-1. In the publish popover, click the preview URL. The URL format is `organization-branch-name.mintlify.app`.
+1. In the publish menu, click the preview URL. The URL format is `organization-branch-name.mintlify.app`.
 
 ### Share your preview
 
 Copy the preview URL and send it to reviewers. The preview updates automatically each time you save to the branch — no need to reshare.
 
 ### Restrict access to previews