fix(mcp): preserve image content blocks in tool results#9570
Closed
masterkain wants to merge 2 commits into
Closed
fix(mcp): preserve image content blocks in tool results#9570masterkain wants to merge 2 commits into
masterkain wants to merge 2 commits into
Conversation
This was referenced Apr 30, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
MEDIA:paths plus amediaarray in the tool resultCallToolResult.contentProblem
Some MCP servers return images as content blocks with
data+mimeTypeand no text.Hermes' MCP bridge only preserved text blocks and
structuredContent, so image-only results were reduced to an empty string. In practice this made tools like Grafana panel image rendering appear blank even though the upstream MCP server had generated a valid PNG.Root cause
In
tools/mcp_tool.py,_make_tool_handler()iteratedresult.contentbut only appended blocks exposing.text.Image blocks were ignored completely.
Fix
data+mimeTypecache_image_from_bytes(...)MEDIA:<path>in the text payload and expose amedialist in the JSON resultVerification
pytest -q tests/tools/test_mcp_structured_content.py