# 2025-12-04: AI Service - Streamable HTTP MCP servers

## Overview

The AI Service has been extended to support a new MCP server transport protocol: `streamable_http`. This option enables streamable HTTP-based communication between agents and custom MCP server implementations alongside the deprecated `sse` transport protocol.

## Modified endpoints

| Endpoint                                                                                                                                                                                                    | Description                                            |
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------ |
| [Searching MCP servers](https://developer.emporix.io/api-references/api-guides/artificial-intelligence/ai-service/api-reference/mcp-server#post-ai-service-tenant-agentic-mcp-servers-search)               | New `streamable_http` transport protocol is supported. |
| [Retrieving MCP server by ID](https://developer.emporix.io/api-references/api-guides/artificial-intelligence/ai-service/api-reference/mcp-server#get-ai-service-tenant-agentic-mcp-servers-mcpserverid)     | New `streamable_http` transport protocol is supported. |
| [Upserting MCP server](https://developer.emporix.io/api-references/api-guides/artificial-intelligence/ai-service/api-reference/mcp-server#put-ai-service-tenant-agentic-mcp-servers-mcpserverid)            | New `streamable_http` transport protocol is supported. |
| [Partially updating MCP server](https://developer.emporix.io/api-references/api-guides/artificial-intelligence/ai-service/api-reference/mcp-server#patch-ai-service-tenant-agentic-mcp-servers-mcpserverid) | New `streamable_http` transport protocol is supported. |

## Known problems

There are no known problems.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://developer.emporix.io/changelog/archive/changelog-2025/2025-12-04-ai.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.