Make MCP references more tool-agnostic

- Update SDK description to emphasize MCP works with various AI assistants and tools
- Change guide link text to "Model Context Protocol integration"
- Update cross-reference to focus on MCP as a standard for tool integration
- Remove specific mentions of Claude to be more inclusive of all MCP-compatible platforms

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <[email protected]>

Author: tpayet

learn/ai_powered_search/conversational_search_with_chat.mdx

@@ -65,9 +65,9 @@ Meilisearch's chat completions consolidates these into one streamlined process:
 - Exact matching is critical
 - Response time is paramount
 
-## Alternative: Using AI assistants with MCP
+## Alternative: Model Context Protocol integration
 
-For developers and power users who want to interact with Meilisearch through AI assistants like Claude, consider using the [Meilisearch Model Context Protocol (MCP) server](/guides/ai/mcp). This allows natural language interaction with your Meilisearch instance through desktop AI applications.
+For developers who want to integrate Meilisearch with AI assistants and automation tools, consider using the [Meilisearch Model Context Protocol (MCP) server](/guides/ai/mcp). MCP enables standardized tool integration across various AI platforms and applications.
 
 ## Architecture overview
 

learn/resources/sdks.mdx

@@ -55,8 +55,8 @@ You can use Meilisearch API wrappers in your favorite language. These libraries
 
 ## AI Assistant tools
 
-- [meilisearch-mcp](https://github.com/meilisearch/meilisearch-mcp): Model Context Protocol server for interacting with Meilisearch through AI assistants like Claude
-  - Guide: [Talk to Meilisearch with Claude desktop](/guides/ai/mcp)
+- [meilisearch-mcp](https://github.com/meilisearch/meilisearch-mcp): Model Context Protocol server for integrating Meilisearch with AI assistants and tools
+  - Guide: [Model Context Protocol integration](/guides/ai/mcp)
 
 ## Other tools