Is it possible to send different data to MCP App vs Agent?

[rohithrangaraju-tomtom]

Pre-submission Checklist

• I have checked that this question would not be more appropriate as an issue in a specific repository
• I have searched existing discussions and documentation for answers

Question Category

• Protocol Specification
• SDK Usage
• Server Implementation
• General Implementation
• Documentation
• Other

Your Question

The Challenge

The same content from a tool result goes to both:

The MCP App (via app.ontoolresult)

The AI agent (as tool result in conversation)
For geospatial tools, this is problematic:

App needs: Full coordinate arrays (legs[].points[] for route polylines, boundary[] for polygons)
Agent needs: Just summaries (distance, duration, counts) - coordinate arrays waste tokens

Is there a way in the current MCP Apps/MCP architecture to:

Send full data to the App for visualization
Send trimmed data to the agent

[Michael-WhiteCapData]

Yes. MCP Apps defines exactly this split:

• put the short, model-facing result in content;
• put the full visualization payload in structuredContent.

For example:

return {
  content: [{
    type: "text",
    text: "Route: 12.4 km, 18 minutes, 3 legs."
  }],
  structuredContent: {
    legs: fullCoordinateArrays,
    boundary: fullBoundaryGeometry
  }
};

The host adds content to model context, while the App receives the structured result through ontoolresult. Declare an outputSchema matching structuredContent so clients can validate the shape.

If the App later needs refresh/pagination/detail operations that should not be visible to the model, expose app-only tools:

_meta: {
  ui: { visibility: ["app"] }
}

That keeps both the large data and the supporting UI operations out of the agent's tool/context budget.

The project overview documents the content split directly: Data delivery. The normative wording is in the Apps specification, which describes structuredContent as UI-optimized data that is not added to model context.