Skip to content

Python: Decode base64 image, audio and blob content from MCP servers #14675

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Jae Birdsall (jaeminbird) wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Python: Decode base64 image, audio and blob content from MCP servers #14675

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions python/semantic_kernel/connectors/mcp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,9 +111,13 @@ def _mcp_content_types_to_kernel_content(
if isinstance(mcp_type, types.TextContent):
return [TextContent(text=mcp_type.text, inner_content=mcp_type)]
if isinstance(mcp_type, types.ImageContent):
return [ImageContent(data=mcp_type.data, mime_type=mcp_type.mimeType, inner_content=mcp_type)]
return [
ImageContent(data=mcp_type.data, data_format="base64", mime_type=mcp_type.mimeType, inner_content=mcp_type)
]
if isinstance(mcp_type, types.AudioContent):
return [AudioContent(data=mcp_type.data, mime_type=mcp_type.mimeType, inner_content=mcp_type)]
return [
AudioContent(data=mcp_type.data, data_format="base64", mime_type=mcp_type.mimeType, inner_content=mcp_type)
]
if isinstance(mcp_type, types.ResourceLink):
return [
BinaryContent(
Expand Down Expand Up @@ -147,6 +151,8 @@ def _mcp_content_types_to_kernel_content(
return [
BinaryContent(
data=mcp_type.resource.blob,
data_format="base64",
mime_type=mcp_type.resource.mimeType,
inner_content=mcp_type,
metadata=mcp_type.annotations.model_dump() if mcp_type.annotations else {},
)
Expand Down
36 changes: 36 additions & 0 deletions python/tests/unit/connectors/mcp/test_mcp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -900,3 +900,39 @@ def echo() -> str:
result = await client.call_tool(expected_name, {})
assert not result.isError
assert result.content == [types.TextContent(type="text", text="hello")]


PNG_BYTES = b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR"
PNG_BASE64 = "iVBORw0KGgoAAAANSUhEUg=="


@pytest.mark.parametrize(
"mcp_content,mime_type",
[
(types.ImageContent(type="image", data=PNG_BASE64, mimeType="image/png"), "image/png"),
(types.AudioContent(type="audio", data=PNG_BASE64, mimeType="audio/wav"), "audio/wav"),
(
types.EmbeddedResource(
type="resource",
resource=types.BlobResourceContents(uri="file:///image.png", blob=PNG_BASE64, mimeType="image/png"),
),
"image/png",
),
],
ids=["image", "audio", "blob_resource"],
)
async def test_mcp_base64_content_is_decoded(mcp_content, mime_type):
plugin = MCPStdioPlugin(name="test", command="echo")
plugin.session = AsyncMock(spec=ClientSession)
plugin.session.call_tool.return_value = types.CallToolResult(content=[mcp_content])
plugin.session.get_prompt.return_value = types.GetPromptResult(
messages=[types.PromptMessage(role="user", content=mcp_content)]
)

[tool_content] = await plugin.call_tool("tool")
[prompt_message] = await plugin.get_prompt("prompt")

for content in (tool_content, prompt_message.items[0]):
assert content.data == PNG_BYTES
assert content.mime_type == mime_type
assert content.data_uri == f"data:{mime_type};base64,{PNG_BASE64}"
Loading