FEAT: Expandable view for MCP tool params and results (TUI) #7041

Open
opened 2026-02-16 18:05:59 -05:00 by yindo · 1 comment
Owner

Originally created by @mynameistito on GitHub (Jan 21, 2026).

Originally assigned to: @rekram1-node on GitHub.

Feature hasn't been suggested before.

  • I have verified this feature I'm about to request 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.

Originally created by @mynameistito on GitHub (Jan 21, 2026). Originally assigned to: @rekram1-node on GitHub. ### Feature hasn't been suggested before. - [x] I have verified this feature I'm about to request 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.
yindo added the opentuidiscussion labels 2026-02-16 18:05:59 -05:00
Author
Owner

@github-actions[bot] commented on GitHub (Jan 21, 2026):

This issue might be a duplicate of existing issues. Please check:

  • #6604: [FEATURE]: MCP Tool Output - Requests MCP tool output to be displayed in TUI
  • #5358: [FEATURE]: Tool output preview - Requests ability to view tool output through preview
  • #9644: [FEATURE]: Show the tool name used for each block showing tool output - Related feature for tool visibility
  • #9655: feat(tui): show running tools and LLM status in sidebar - Related tool visibility feature

Feel free to ignore if none of these address your specific case.

@github-actions[bot] commented on GitHub (Jan 21, 2026): This issue might be a duplicate of existing issues. Please check: - #6604: [FEATURE]: MCP Tool Output - Requests MCP tool output to be displayed in TUI - #5358: [FEATURE]: Tool output preview - Requests ability to view tool output through preview - #9644: [FEATURE]: Show the tool name used for each block showing tool output - Related feature for tool visibility - #9655: feat(tui): show running tools and LLM status in sidebar - Related tool visibility feature Feel free to ignore if none of these address your specific case.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#7041