feat: Add multimodal output support for Jupyter cell execution #75
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
added 3 commits
September 24, 2025 15:33
This commit introduces comprehensive multimodal output support that allows the MCP server to return actual image content instead of text placeholders when executing Jupyter cells. Key Changes: - Add ALLOW_IMG_OUTPUT environment variable to control multimodal output behavior - New config_env.py module for robust environment variable management - Enhanced utils.py to extract and return PNG images as ImageContent objects - Updated server.py function signatures to support Union[str, ImageContent] returns - Comprehensive test coverage for multimodal functionality with PIL-based image generation - Updated documentation and CI workflows to support the new feature - README.md updated with Docker configuration examples The feature is backward compatible - when ALLOW_IMG_OUTPUT is disabled, the server falls back to text placeholders for images.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
#69
This commit introduces comprehensive multimodal output support that allows the MCP server to return actual image content instead of text placeholders when executing Jupyter cells.
Key Changes:
The feature is backward compatible - when ALLOW_IMG_OUTPUT is disabled, the server falls back to text placeholders for images.