io.github.alexalexalex222/frontend-design-loop-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| frontend_design_loop_solve | Generate multiple patch candidates, run gates, (optionally) run vision, pick a winner. Notes:
|
| frontend_design_loop_design | Design-first wrapper around Use this when you want Frontend Design Loop to actively improve the UI, not just verify a host-authored patch bundle. |
| frontend_design_loop_evalD | MCP tool wrapper for Returns:
|
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion with other tools. The tool's purpose is singular and unambiguous.
With a single tool, naming consistency is trivially perfect. The name uses a descriptive underscore-separated pattern.
A single tool for a 'frontend design loop' is far too few. The server promises a loop of design activities but only provides evaluation, missing creation, modification, or iteration tools.
The tool surface is severely incomplete. A design loop typically involves multiple steps (create, review, modify, test), but only an evaluation tool is provided, leaving critical gaps.