Feature hasn't been suggested before.
Describe the enhancement you want to request
Problem
Currently, when an MCP tool is executed in the chat, the UI only shows the tool name with a gear icon. There is no way for the user to click and inspect the arguments passed to the tool, or the resulting context/payload that the tool returned.
Benefits
- Easier Debugging: Instantly see if a tool failed because of bad inputs or a bad response.
- Full Transparency: Know exactly what context and data the LLM is using to make its decisions.
- Developer Efficiency: Eliminates flying blind not knowing what the mcp called/gave the LLM.
Use Case
A user asks the LLM to fetch error logs from an external service. The tool executes successfully, but I wants to see the raw log output that was returned to the model to verify the issue themselves, rather than just relying on the model's summary.
Feature hasn't been suggested before.
Describe the enhancement you want to request
Problem
Currently, when an MCP tool is executed in the chat, the UI only shows the tool name with a gear icon. There is no way for the user to click and inspect the arguments passed to the tool, or the resulting context/payload that the tool returned.
Benefits
Use Case
A user asks the LLM to fetch error logs from an external service. The tool executes successfully, but I wants to see the raw log output that was returned to the model to verify the issue themselves, rather than just relying on the model's summary.