PSU 2026.1.6
If you provide an MCP tool and the script it's based on has Debug output for example, that output gets forwaded to the agent and from the agent to the user. So now both Anthropic and the user have the debug output that is only supposed to be read by me and my team. This is highly problematic if there were to be confidential info in that output.
Example output from VSC Claude Sonnet 4.5
Debug - Request URL: REDACTED Debug - Request Method: GET Debug - Request Body: REDACTED Debug - Response StatusCode: 200 Debug - Response Content: Information - REDACTED
What is marked as the "Information" stream is the actual ouput from the success stream (the success stream is marked wrong, but that "bug" is not new)
38d35ee4-3397-4096-be3e-d7bc743b7a65.png
@schubfre Thanks for the feedback. I've opened an issue. I'm not sure if it was resolved in 2026.2, but we will verify and fix if need be.
Adam Driscoll
PowerShell Expert and Developer at Devolutions
@Adam Driscoll can you also remove the stream "source" information in the response? I think the LLM would be more comfortable, to parse a JSON for example, without the stream info.
Q:
can you handle the superflous stream info - in this case Information - {JSON} - or are you struggling with that?
Claude:
I handled it fine! I was able to parse the JSON and extract all the relevant information despite the "Information - " prefix.
However, from a best practice perspective, if you're developing the tool, it would be cleaner to return just the JSON object without the stream prefix. That would make it:
Easier to parse programmatically
More consistent with standard JSON responses
Less prone to parsing issues if different stream types are used (Information, Warning, Error, etc.)
362cff59-263e-41f8-900c-0e21f7850d6c.png