反馈工具
MCP 服务配置
复制以下 JSON 到 OPClaw 或其他 MCP 客户端的配置文件中即可使用
{
"mcpServers": {
"mcp-feedback-elicitation": {
"args": [
"mcp-feedback-elicitation"
],
"command": "npx",
"timeout": 86400000
}
}
}可用工具 （1 个）
该服务在 MCP 协议中暴露的工具，AI 可按需调用
interactive_feedback 2 个参数
Interactive feedback collection tool for LLM agents. USAGE RULES: 1. During any process, task, or conversation, whether asking, replying, or completing phased tasks, you must call this tool to ask for feedback. 2. Unless receiving termination instructions, all steps must repeatedly call this tool. 3. Whenever user feedback is received, if the feedback content is not empty, you must call this tool again and adjust behavior based on the feedback content. 4. Only when the user explicitly indicates "end" or "no more interaction needed" can you stop calling this tool, and the process is considered complete. 5. You should summarize what have done, and provide project directory through args to let user know what you have done to provide feedback for next step. Args: project_directory: Project directory path for context summary: Summary of AI work completed for user review timeout: Timeout in seconds for waiting user feedback (default: 600 seconds) Returns: list: List containing TextContent and MCPImage objects representing user feedback
该工具无需必填参数，直接调用即可
服务介绍
An interactive feedback collection server based on the Model Context Protocol (MCP), using MCP Elicitation features to replace traditional Web UI solutions, providing a standardized user feedback collection experience.
Project Background
- 🤖 AI Generated: This project was generated using Claude Sonnet 4.
- 📚 Reference Project: Implemented with reference to mcp-feedback-enhanced. For more advanced features such as image uploads and session management, please use the mcp-feedback-enhanced project.
- 🔧 Technical Features: Uses MCP Elicitation instead of Web UI, requiring client support for Elicitation functionality.
Compatibility
Currently, VS Code 1.102+ supports the MCP Elicitation feature.
Quick Start
Add the following configuration in mcp.json:
json5
"mcp-feedback-elicitation": {
"command": "npx",
"args": [
"mcp-feedback-elicitation"
],
"timeout": 86400000,
"autoApprove": [
"interactive_feedback"
],
"env": {
// "FEEDBACK_TEMPLATE": "=== 用户反馈 ===\n{{feedback}}",
// "FEEDBACK_PROMPT": "自定义工具描述，用于 AI 助手了解工具用途和使用规则"
}
}
Environment Variable Configuration
FEEDBACK_TEMPLATE
Controls the format template for feedback output, using {{feedback}} as a placeholder to insert the actual user feedback content.
Example Configuration:
json
"FEEDBACK_TEMPLATE": "📝 反馈内容：{{feedback}}\n\n✅ 请及时处理相关事项"
FEEDBACK_PROMPT
Custom description of the tool, which the AI assistant uses to understand the purpose and usage rules of the tool.
Multilingual Support Example:
json
// Chinese environment
"FEEDBACK_PROMPT": "交互式反馈收集工具。在任务执行过程中调用此工具收集用户反馈。必须重复调用直到用户明确表示结束。"
// English environment
"FEEDBACK_PROMPT": "Interactive feedback collection tool. Call this tool to collect user feedback during task execution. Must call repeatedly until user explicitly says 'end'."
// Japanese environment
"FEEDBACK_PROMPT": "インタラクティブフィードバック収集ツール。タスク実行中にこのツールを呼び出してユーザーフィードバックを収集します。ユーザーが明確に終了を示すまで繰り返し呼び出す必要があります。"
Disclaimer
This project is AI-generated. Please assess the risks yourself when using it; the author assumes no responsibility.
