modelcontextprotocol / modelcontextprotocol/python-sdk

PydanticSchemaGenerationError: Unable to generate pydantic-core schema for Image type

Open
#1,060 4 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

bug P2 ready for work
Dominant language
Python
Stars
24.3k
Forks
4k
Avg merge
1d 1h
Merged PRs (30d)
31

Description

Initial Checks
Description

The Image type in question is imported like this: from mcp.server.fastmcp.utilities.types import Image

We are upgrading our dependency on mcp from 1.9.4 to 1.10.1.

Once on 1.10.1 our application and tests began to fail with error like this:

pydantic.errors.PydanticSchemaGenerationError: Unable to generate pydantic-core schema
for <class 'mcp.server.fastmcp.utilities.types.Image'>. Set `arbitrary_types_allowed=True` in
the model_config to ignore this error or implement `__get_pydantic_core_schema__` on your
type to fully support it.

I found a test tool function among this repo's unit tests, that is pretty close to the mixed content
use case in our server. So I tweaked it to create a repro case for you:

diff --git a/tests/server/fastmcp/test_server.py b/tests/server/fastmcp/test_server.py
index c30930f..20c25af 100644
--- a/tests/server/fastmcp/test_server.py
+++ b/tests/server/fastmcp/test_server.py
@@ -194,12 +194,12 @@ def image_tool_fn(path: str) -> Image:
     return Image(path)
 
 
-def mixed_content_tool_fn() -> list[ContentBlock]:
-    return [
-        TextContent(type="text", text="Hello"),
-        ImageContent(type="image", data="abc", mimeType="image/png"),
+def mixed_content_tool_fn() -> tuple[str, Image, AudioContent]:
+    return (
+        "Hello",
+        Image(data=b"abc", format="png"),
         AudioContent(type="audio", data="def", mimeType="audio/wav"),
-    ]
+    )
 
 
 class TestServerTools:
@@ -311,7 +311,7 @@ class TestServerTools:
             assert content1.text == "Hello"
             assert isinstance(content2, ImageContent)
             assert content2.mimeType == "image/png"
-            assert content2.data == "abc"
+            assert content2.data == "YWJj"
             assert isinstance(content3, AudioContent)
             assert content3.mimeType == "audio/wav"
             assert content3.data == "def"

test_tool_mixed_content fails with PydanticSchemaGenerationError on 1.10.1 but succeeds on 1.9.4.

Python & MCP Python SDK
Python 3.12, mcp 1.10.1

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with tests/server/fastmcp/test_server.py, especially test_tool_mixed_content and the mixed_content_tool_fn reproduction. Read the Image type imported from mcp.server.fastmcp.utilities.types and trace how its tuple return annotation is processed under mcp 1.10.1. Done means the mixed-content test passes without PydanticSchemaGenerationError while preserving the expected image and audio content assertions.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
62/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.