gl-mcp-feedback
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_DEBUG | No | 调试模式,值为true/false | false |
| MCP_LANGUAGE | No | 强制指定界面语言,支持 zh-TW, zh-CN, en | 自动检测 |
| MCP_WEB_HOST | No | Web UI 主机绑定,IP地址或主机名 | 127.0.0.1 |
| MCP_WEB_PORT | No | Web UI 端口,1024-65535 | 8765 |
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
} |
| 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 | Open a Web UI to collect interactive feedback from the user. This tool is the PRIMARY communication channel with the user. The full list of "when to call" scenarios lives in the project's gl-mcp-feedback user rules; this docstring covers how to use this tool. Strict prohibitions:
- While this tool is available, DO NOT invoke Cursor's built-in
Queued messages:
While you work between two calls, the user can keep typing in the
Web UI; those messages are queued (at most 3) and reach you in one
of two ways, both under a header starting with
Args:
project_directory: Absolute or relative project path. Defaults to cwd.
summary: Required Markdown summary. No empty string, no placeholder.
timeout: Seconds to wait for user feedback. Values above Returns:
ToolResult: TextContent with the user's text feedback plus
MCPImage objects for any uploaded images. An empty result
means the user skipped — re-call to ask why. A result starting
with |
| get_system_infoA | 获取系统环境信息 Returns: str: JSON 格式的系统信息 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| chat | 通过 Web UI 与用户开始互动反馈对话。 使用此 prompt 快速启动反馈交流。 AI 会调用 interactive_feedback 工具打开 Web UI, 通过浏览器界面与用户进行互动。 |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have completely distinct purposes: one opens an interactive feedback UI, the other returns system environment information. There is no plausible scenario where an agent would confuse them.
Both names use snake_case and are readable, but `interactive_feedback` is a noun phrase while `get_system_info` follows a verb_noun pattern. The deviation is minor and does not impede understanding.
Two tools is thin for a dedicated feedback server. `interactive_feedback` is clearly the core tool, while `get_system_info` feels like an unrelated utility that does not support the feedback domain.
The primary feedback interaction is well covered, including queued messages and timeouts. However, there is no tool for retrieving prior feedback history, managing sessions, or inspecting feedback results outside the immediate call.