Accept Image and Audio helpers as prompt message content

Tools already convert the Image/Audio helpers to ImageContent/AudioContent;
prompt messages rejected them with a pydantic validation error, forcing
UserMessage(Image(...).to_image_content()). Message.__init__ now performs the
same conversion, so UserMessage(Image(...)) works, including via the dict form.

Author: maxisbey

src/mcp/server/mcpserver/prompts/base.py

@@ -13,6 +13,7 @@
 
 from mcp.server.mcpserver.utilities.context_injection import find_context_parameter, inject_context
 from mcp.server.mcpserver.utilities.func_metadata import func_metadata
+from mcp.server.mcpserver.utilities.types import Audio, Image
 from mcp.shared._callable_inspection import is_async_callable
 from mcp.shared.exceptions import MCPError
 
@@ -22,14 +23,22 @@
 
 
 class Message(BaseModel):
-    """Base class for all prompt messages."""
+    """Base class for all prompt messages.
+
+    `content` may be a plain string (wrapped in `TextContent`), an `Image` or `Audio`
+    helper (converted to `ImageContent` / `AudioContent`), or any ready-made content block.
+    """
 
     role: Literal["user", "assistant"]
     content: ContentBlock
 
-    def __init__(self, content: str | ContentBlock, **kwargs: Any):
+    def __init__(self, content: str | ContentBlock | Image | Audio, **kwargs: Any):
         if isinstance(content, str):
             content = TextContent(type="text", text=content)
+        elif isinstance(content, Image):
+            content = content.to_image_content()
+        elif isinstance(content, Audio):
+            content = content.to_audio_content()
         super().__init__(content=content, **kwargs)
 
 
@@ -38,7 +47,7 @@ class UserMessage(Message):
 
     role: Literal["user", "assistant"] = "user"
 
-    def __init__(self, content: str | ContentBlock, **kwargs: Any):
+    def __init__(self, content: str | ContentBlock | Image | Audio, **kwargs: Any):
         super().__init__(content=content, **kwargs)
 
 
@@ -47,7 +56,7 @@ class AssistantMessage(Message):
 
     role: Literal["user", "assistant"] = "assistant"
 
-    def __init__(self, content: str | ContentBlock, **kwargs: Any):
+    def __init__(self, content: str | ContentBlock | Image | Audio, **kwargs: Any):
         super().__init__(content=content, **kwargs)
 
 

tests/server/mcpserver/prompts/test_base.py

@@ -3,15 +3,17 @@
 
 import pytest
 from mcp_types import (
+    AudioContent,
     ElicitRequest,
     ElicitRequestFormParams,
     EmbeddedResource,
+    ImageContent,
     InputRequiredResult,
     TextContent,
     TextResourceContents,
 )
 
-from mcp.server.mcpserver import Context
+from mcp.server.mcpserver import Audio, Context, Image
 from mcp.server.mcpserver.prompts.base import AssistantMessage, Message, Prompt, UserMessage
 
 
@@ -243,3 +245,18 @@ def asking_prompt() -> InputRequiredResult:
     prompt = Prompt.from_function(asking_prompt)
     result = await prompt.render(None, Context())
     assert result is sentinel
+
+
+@pytest.mark.parametrize(
+    ("helper", "expected"),
+    [
+        (Image(data=b"img", format="png"), ImageContent(type="image", data="aW1n", mime_type="image/png")),
+        (Audio(data=b"snd", format="wav"), AudioContent(type="audio", data="c25k", mime_type="audio/wav")),
+    ],
+)
+def test_message_converts_image_and_audio_helpers_to_content_blocks(
+    helper: Image | Audio, expected: ImageContent | AudioContent
+) -> None:
+    """SDK-defined: prompt messages accept the same `Image`/`Audio` helpers tools return."""
+    assert UserMessage(helper).content == expected
+    assert AssistantMessage(content=helper).content == expected