Ai Intervention Agent

Add to Cursor Add to VS Code Add to Claude Add to ChatGPT Add to Codex Add to Gemini

AI Intervention Agent

Real-time user intervention for MCP agents.

English | 简体中文

When using AI CLIs/IDEs, agents can drift from your intent. This project gives you a simple way to intervene at key moments, review context in a Web UI, and send your latest instructions via interactive_feedback so the agent can continue on track.

Works with Cursor, VS Code, Claude Code, Augment, Windsurf, Trae, and more.

Quick start

1. Install:

pip install ai-intervention-agent

# or
uv add ai-intervention-agent

2. Configure your AI tool to launch the MCP server via uvx:

{
  "mcpServers": {
    "ai-intervention-agent": {
      "command": "uvx",
      "args": ["ai-intervention-agent"],
      "timeout": 600,
      "autoApprove": ["interactive_feedback"]
    }
  }
}

[!NOTE] > interactive_feedback is a long-running tool. Some clients have a hard request timeout, so the Web UI provides a countdown + auto re-submit option to keep sessions alive.

- Only ask me through the MCP `ai-intervention-agent` tool; do not ask directly in chat or ask for end-of-task confirmation in chat.
- If a tool call fails, keep asking again through `ai-intervention-agent` instead of making assumptions, until the tool call succeeds.

ai-intervention-agent usage details:

- If requirements are unclear, use `ai-intervention-agent` to ask for clarification with predefined options.
- If there are multiple approaches, use `ai-intervention-agent` to ask instead of deciding unilaterally.
- If a plan/strategy needs to change, use `ai-intervention-agent` to ask instead of deciding unilaterally.
- Before finishing a request, always ask for feedback via `ai-intervention-agent`.
- Do not end the conversation/request unless the user explicitly allows it via `ai-intervention-agent`.

Screenshots

_{Feedback page (auto switches between dark/light)}

Key features

• Real-time intervention: the agent pauses and waits for your input via interactive_feedback
• Web UI: Markdown, code highlighting, and math rendering
• Multi-task: tab switching with independent countdown timers
• Auto re-submit: keep sessions alive by auto-submitting at timeout
• Notifications: web / sound / system / Bark
• SSH-friendly: great with port forwarding

VS Code extension (optional)

Configuration

Architecture

flowchart TD
  subgraph CLIENTS["AI clients"]
    AI_CLIENT["AI CLI / IDE<br/>(Cursor, VS Code, Claude Code, ...)"]
  end

  subgraph MCP_PROC["MCP server process"]
    MCP_SRV["ai-intervention-agent<br/>(server.py)"]
    MCP_TOOL["MCP tool<br/>interactive_feedback"]
    CFG_MGR["Config manager<br/>(config_manager.py)"]
    NOTIF_MGR["Notification manager<br/>(notification_manager.py)"]
  end

  subgraph WEB_PROC["Web UI process"]
    WEB_SRV["Web UI service<br/>(web_ui.py / Flask)"]
    HTTP_API["HTTP API<br/>(/api/*)"]
    TASK_Q["Task queue<br/>(task_queue.py)"]
    WEB_SRV --> HTTP_API
    WEB_SRV --> TASK_Q
  end

  subgraph USER_UI["User interfaces"]
    BROWSER["Browser"]
    VSCODE["VS Code extension<br/>(Webview)"]
  end

  CFG_FILE["config.jsonc<br/>(user config directory)"]

  AI_CLIENT -->|MCP call| MCP_TOOL
  MCP_SRV -->|exposes| MCP_TOOL

  MCP_TOOL -->|ensure Web UI running| WEB_SRV
  MCP_TOOL <-->|create task / poll result| HTTP_API

  BROWSER <-->|HTTP| HTTP_API
  VSCODE <-->|HTTP| HTTP_API

  CFG_MGR <-->|read/write| CFG_FILE
  WEB_SRV <-->|read| CFG_FILE

  MCP_SRV --> NOTIF_MGR
  NOTIF_MGR -->|web / sound / system / Bark| USER["User"]

Documentation

• API docs index: docs/api/index.md
• API docs (简体中文): docs/api.zh-CN/index.md
• DeepWiki: deepwiki.com/xiadengma/ai-intervention-agent

Related projects

• interactive-feedback-mcp
• mcp-feedback-enhanced
• cunzhi
• other interactive-feedback-mcp

License

MIT License