What specific problem does this solve?

Who is affected:
Anyone who connect to databases and comes across queries that returns too much data (> context size limit).

When does this happen: See above.
What's the current bheavior:
The entire MCP response gets embedded into the context I think? And the whole AI iteration process grinds to a half. The model struggles to even condense the context (with the entire MCP response embedded).

What's the impact:

• AI stops working
• The user is unable to process anything that returns too much data.

Lastly, most of the time, it's relatively unproductive to get LLM to consume large data set and trying to make it return the correct result. I find more success in have the data saved as a file and having AI write some scripts or use other CLI / bash commands / scripts to work with the data.

Additional context (optional)

No response

Roo Code Task Links (Optional)

No response

Request checklist

• I've searched existing Issues and Discussions for duplicates
• This describes a specific problem with clear impact and context

Interested in implementing this?

• Yes, I'd like to help implement this feature

Implementation requirements

• I understand this needs approval before implementation begins

How should this be solved? (REQUIRED if contributing, optional otherwise)

No response

How will we know it works? (Acceptance Criteria - REQUIRED if contributing, optional otherwise)

No response

Technical considerations (REQUIRED if contributing, optional otherwise)

No response

Trade-offs and risks (REQUIRED if contributing, optional otherwise)

No response