MCP Feedback Enhanced
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_DEBUG | No | Debug mode | false |
| MCP_LANGUAGE | No | Force UI language | Auto-detect |
| MCP_WEB_HOST | No | Web UI host binding | 127.0.0.1 |
| MCP_WEB_PORT | No | Web UI port | 8765 |
| MCP_DESKTOP_MODE | No | Desktop application mode | false |
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| interactive_feedbackA | Interactive feedback collection tool for LLM agents. USAGE RULES:
|
| get_system_infoA | 獲取系統環境資訊 Returns: str: JSON 格式的系統資訊 |
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 2 tools
The two tools serve entirely different purposes: interactive_feedback collects user feedback, while get_system_info retrieves system environment details. There is no overlap or confusion between them.
The naming conventions are mixed: 'interactive_feedback' uses an adjective-noun structure, while 'get_system_info' uses a verb-noun structure. Although both use snake_case, the lack of a consistent verb-first pattern across the set reduces coherence.
With only two tools, the server feels thin for its stated purpose of enhanced feedback collection. The count is borderline, as it sits at the low end of the acceptable range but may be insufficient for robust workflows.
The domain appears to be feedback collection, but the tool surface is severely limited. There is only one feedback-related tool (interactive_feedback) with no way to retrieve, update, or manage feedback history. The unrelated get_system_info tool does little to round out the domain, leaving significant gaps.