Lets AI coding assistants pause and ask the user for feedback, enabling human-in-the-loop workflows.
接入配置
选择客户端，复制配置，再按项目文档补齐环境变量。
claude mcp add interactive-feedback -- uv --directory path/to/interactive-feedback-mcp run server.py~/.codex/config.toml
[mcp_servers.interactive-feedback]
command = "uv"
args = ["--directory", "path/to/interactive-feedback-mcp", "run", "server.py"]
# codex mcp add interactive-feedback -- uv --directory path/to/interactive-feedback-mcp run server.py~/.cursor/mcp.json
{
"mcpServers": {
"interactive-feedback": {
"command": "uv",
"args": [
"--directory",
"path/to/interactive-feedback-mcp",
"run",
"server.py"
]
}
}
}.vscode/mcp.json
{
"servers": {
"interactive-feedback": {
"type": "stdio",
"command": "uv",
"args": [
"--directory",
"path/to/interactive-feedback-mcp",
"run",
"server.py"
]
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"interactive-feedback": {
"command": "uv",
"args": [
"--directory",
"path/to/interactive-feedback-mcp",
"run",
"server.py"
]
}
}
}claude_desktop_config.json
{
"mcpServers": {
"interactive-feedback": {
"command": "uv",
"args": [
"--directory",
"path/to/interactive-feedback-mcp",
"run",
"server.py"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"interactive-feedback": {
"command": "uv",
"args": [
"--directory",
"path/to/interactive-feedback-mcp",
"run",
"server.py"
]
}
}
}