Metadata-Version: 2.4
Name: ai-intervention-agent
Version: 1.6.4
Summary: AI Intervention Agent: MCP server enabling real-time user intervention in AI-assisted development workflows.
Project-URL: Homepage, https://github.com/xiadengma/ai-intervention-agent
Project-URL: Repository, https://github.com/xiadengma/ai-intervention-agent
Project-URL: Issues, https://github.com/xiadengma/ai-intervention-agent/issues
Project-URL: Discussions, https://github.com/xiadengma/ai-intervention-agent/discussions
Project-URL: Documentation, https://github.com/xiadengma/ai-intervention-agent#readme
Project-URL: Changelog, https://github.com/xiadengma/ai-intervention-agent/blob/main/CHANGELOG.md
Project-URL: Release notes, https://github.com/xiadengma/ai-intervention-agent/releases
Author-email: xiadengma <52972447+XIADENGMA@users.noreply.github.com>
License-Expression: MIT
License-File: LICENSE
Keywords: agent,ai,claude,cursor,feedback,intervention,mcp
Classifier: Development Status :: 5 - Production/Stable
Classifier: Environment :: Web Environment
Classifier: Framework :: Flask
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Natural Language :: Chinese (Simplified)
Classifier: Natural Language :: English
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.11
Requires-Dist: brotli>=1.2.0
Requires-Dist: fastmcp>=3.0.0
Requires-Dist: flasgger>=0.9.7
Requires-Dist: flask-compress>=1.15.0
Requires-Dist: flask-cors>=5.0.0
Requires-Dist: flask-limiter>=4.0.0
Requires-Dist: flask>=3.1.3
Requires-Dist: httpx>=0.28.1
Requires-Dist: loguru>=0.7.3
Requires-Dist: markdown>=3.8.0
Requires-Dist: platformdirs>=4.3.0
Requires-Dist: plyer>=2.1.0
Requires-Dist: psutil>=6.1.0
Requires-Dist: pydantic>=2.0.0
Requires-Dist: pygments>=2.18.0
Requires-Dist: tomlkit>=0.14.0
Requires-Dist: zeroconf>=0.146.0
Provides-Extra: dev
Requires-Dist: pre-commit>=4.0.0; extra == 'dev'
Requires-Dist: pytest-cov>=6.2.1; extra == 'dev'
Requires-Dist: pytest-timeout>=2.3.0; extra == 'dev'
Requires-Dist: pytest>=9.0.3; extra == 'dev'
Requires-Dist: rcssmin>=1.1.2; extra == 'dev'
Requires-Dist: rjsmin>=1.2.5; extra == 'dev'
Requires-Dist: ruff>=0.8.0; extra == 'dev'
Requires-Dist: ty; extra == 'dev'
Description-Content-Type: text/markdown

<div align="center">
  <a href="https://github.com/xiadengma/ai-intervention-agent">
    <img src="src/ai_intervention_agent/icons/icon.svg" width="160" height="160" alt="AI Intervention Agent" />
  </a>

  <h2>AI Intervention Agent</h2>

  <p><strong>Real-time user intervention for MCP agents.</strong></p>

  <p>
    <a href="https://github.com/xiadengma/ai-intervention-agent/actions/workflows/test.yml">
      <img src="https://img.shields.io/github/actions/workflow/status/xiadengma/ai-intervention-agent/test.yml?branch=main&label=tests&style=flat-square&logo=github" alt="Tests" />
    </a>
    <a href="https://pypi.org/project/ai-intervention-agent/">
      <img src="https://img.shields.io/pypi/v/ai-intervention-agent?style=flat-square&logo=pypi&logoColor=white" alt="PyPI" />
    </a>
    <a href="https://www.python.org/downloads/">
      <img src="https://img.shields.io/pypi/pyversions/ai-intervention-agent?style=flat-square&logo=python&logoColor=white" alt="Python versions" />
    </a>
    <a href="https://github.com/xiadengma/ai-intervention-agent/actions/workflows/scorecard.yml">
      <img src="https://img.shields.io/github/actions/workflow/status/xiadengma/ai-intervention-agent/scorecard.yml?branch=main&label=OpenSSF&style=flat-square&logo=securityscorecard&logoColor=white" alt="OpenSSF Scorecard" />
    </a>
    <a href="https://github.com/xiadengma/ai-intervention-agent/blob/main/LICENSE">
      <img src="https://img.shields.io/github/license/xiadengma/ai-intervention-agent?style=flat-square&color=success" alt="License" />
    </a>
  </p>

  <p>
    English | <a href="./README.zh-CN.md">简体中文</a>
  </p>
</div>

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

### Quickest: ask your AI to install it for you

If your IDE/CLI has an AI agent (Cursor, Claude Code, VS Code, Windsurf, Trae, Augment, ...), paste the prompt below in chat and let it write the config for you.

<details>
<summary>Click to copy the install prompt</summary>

```text
Please configure my IDE / AI tool to use the `ai-intervention-agent` MCP server:

1. Locate the correct MCP config file for my current IDE
   (e.g. `.cursor/mcp.json` or `~/.cursor/mcp.json` for Cursor,
    `~/.claude.json` for Claude Code,
    `.vscode/mcp.json` for VS Code).
2. Add this entry under `mcpServers`:
   - command: `uvx`
   - args: `["ai-intervention-agent"]`
   - timeout: 600
   - autoApprove: `["interactive_feedback"]`
3. Append the project's recommended prompt rules
   (the "Prompt snippet (copy/paste)" block in this README)
   to my agent rules / system prompt, so the agent always asks me
   through `interactive_feedback` instead of ending tasks silently.
4. Verify by listing MCP servers and confirming `ai-intervention-agent` is loaded.
```

</details>

### Option 1: Using `uvx` (Recommended)

[<img src="https://img.shields.io/badge/Install%20Server-Cursor-black?style=flat-square" alt="Install in Cursor">](https://cursor.com/en/install-mcp?name=ai-intervention-agent&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJhaS1pbnRlcnZlbnRpb24tYWdlbnQiXSwidGltZW91dCI6NjAwLCJhdXRvQXBwcm92ZSI6WyJpbnRlcmFjdGl2ZV9mZWVkYmFjayJdfQ%3D%3D)
[<img src="https://img.shields.io/badge/Install%20Server-VS%20Code-0098FF?style=flat-square" alt="Install in VS Code">](https://vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%257B%2522name%2522%253A%2522ai-intervention-agent%2522%252C%2522command%2522%253A%2522uvx%2522%252C%2522args%2522%253A%255B%2522ai-intervention-agent%2522%255D%252C%2522timeout%2522%253A600%252C%2522autoApprove%2522%253A%255B%2522interactive_feedback%2522%255D%257D)

Configure your AI tool to launch the MCP server directly via `uvx` (this automatically installs and runs the latest version):

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

### Option 2: Using `pip`

1. First, install the package manually (please remember to manually `pip install --upgrade ai-intervention-agent` periodically to get updates):

```bash
pip install ai-intervention-agent
```

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

```json
{
  "mcpServers": {
    "ai-intervention-agent": {
      "command": "ai-intervention-agent",
      "args": [],
      "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.
>
> - Default: `feedback.frontend_countdown=240` seconds
> - Range: `0` (disabled) or `[10, 3600]` seconds. The default 240 stays
>   under the common 300s session hard timeout; raise it intentionally
>   when your client allows longer turns.

3. (Optional) Customize your config:

- On first run, `config.toml` will be created under your OS user config directory (see [docs/configuration.md](docs/configuration.md)).
- Example:

```toml
[web_ui]
port = 8080

[feedback]
frontend_countdown = 240
backend_max_wait = 600
```

<details>
<summary>Prompt snippet (copy/paste)</summary>

```text
- 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`.
```

</details>

## Screenshots

<p align="center">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset=".github/assets/desktop_dark_content.png">
    <img alt="Desktop - feedback page (multi-task tabs, code highlighting, predefined options)" src=".github/assets/desktop_light_content.png" width="600" height="501" />
  </picture>
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset=".github/assets/mobile_dark_content.png">
    <img alt="Mobile - feedback page" src=".github/assets/mobile_light_content.png" width="180" height="447" />
  </picture>
</p>

<p align="center"><sub>Feedback page · auto switches between dark/light · multi-task tabs with independent countdowns</sub></p>

<details>
<summary>More screenshots (empty state + settings)</summary>

<p align="center">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset=".github/assets/desktop_dark_no_content.png">
    <img alt="Desktop - empty state" src=".github/assets/desktop_light_no_content.png" width="600" height="422" />
  </picture>
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset=".github/assets/mobile_dark_no_content.png">
    <img alt="Mobile - empty state" src=".github/assets/mobile_light_no_content.png" width="180" height="390" />
  </picture>
</p>

<p align="center"><sub>Empty state · waiting for the next interactive request</sub></p>

<p align="center">
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset=".github/assets/desktop_dark_settings.png">
    <img alt="Desktop - settings (notifications, Bark, feedback)" src=".github/assets/desktop_light_settings.png" width="600" height="422" />
  </picture>
  <picture>
    <source media="(prefers-color-scheme: dark)" srcset=".github/assets/mobile_dark_settings.png">
    <img alt="Mobile - settings" src=".github/assets/mobile_light_settings.png" width="180" height="390" />
  </picture>
</p>

<p align="center"><sub>Settings · notifications · Bark · sound · feedback countdown · auto switches between dark/light</sub></p>

</details>

## 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 (loopback URLs auto-suppressed; LAN-IP suggestion surfaced in settings)
- **SSH / LAN friendly**: works behind port forwarding; mDNS publishes a `<host>.local` URL when the local network supports it

> Architecture diagram, "how it works" flow, production middleware chain,
> server self-info resource, and MCP-spec compliance details live under
> [`docs/api/index.md`](docs/api/index.md) and
> [`docs/mcp_tools.md`](docs/mcp_tools.md).

## VS Code extension (optional)

<p>
  <a href="https://open-vsx.org/extension/xiadengma/ai-intervention-agent">
    <img src="https://img.shields.io/open-vsx/v/xiadengma/ai-intervention-agent?label=Open%20VSX&style=flat-square&logo=eclipseide&logoColor=white" alt="Open VSX version" />
  </a>
  <a href="https://open-vsx.org/extension/xiadengma/ai-intervention-agent">
    <img src="https://img.shields.io/open-vsx/dt/xiadengma/ai-intervention-agent?label=downloads&style=flat-square" alt="Open VSX downloads" />
  </a>
  <a href="https://open-vsx.org/extension/xiadengma/ai-intervention-agent">
    <img src="https://img.shields.io/open-vsx/rating/xiadengma/ai-intervention-agent?label=rating&style=flat-square" alt="Open VSX rating" />
  </a>
</p>

| Item                           | Value                                                                                                                                                                                                                                                               |
| ------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Purpose                        | Embed the interaction panel into VS Code’s sidebar to avoid switching to a browser.                                                                                                                                                                                 |
| Install (Open VSX)             | [Open VSX](https://open-vsx.org/extension/xiadengma/ai-intervention-agent)                                                                                                                                                                                          |
| Download VSIX (GitHub Release) | [GitHub Releases](https://github.com/xiadengma/ai-intervention-agent/releases/latest)                                                                                                                                                                               |
| Setting                        | `ai-intervention-agent.serverUrl` (should match your Web UI URL, e.g. `http://localhost:8080`; you can change `web_ui.port` in [`config.toml.default`](config.toml.default))                                                                                        |
| Other settings                 | `ai-intervention-agent.logLevel` (Output → AI Intervention Agent). macOS native notifications are enabled by default and can be toggled in the sidebar's **Notification Settings** panel. See [`packages/vscode/README.md`](packages/vscode/README.md) for the full settings list and the AppleScript executor security model.                                                                |

## Configuration

| Item             | Value                                                                                          |
| ---------------- | ---------------------------------------------------------------------------------------------- |
| Docs (English)   | [docs/configuration.md](docs/configuration.md)                                                 |
| Docs (简体中文)  | [docs/configuration.zh-CN.md](docs/configuration.zh-CN.md)                                     |
| Default template | [`config.toml.default`](config.toml.default) (on first run it will be copied to `config.toml`) |

| OS      | User config directory                                  |
| ------- | ------------------------------------------------------ |
| Linux   | `~/.config/ai-intervention-agent/`                     |
| macOS   | `~/Library/Application Support/ai-intervention-agent/` |
| Windows | `%APPDATA%/ai-intervention-agent/`                     |

## Documentation

- **Docs index** (by audience): [`docs/README.md`](docs/README.md) · [`docs/README.zh-CN.md`](docs/README.zh-CN.md)
- **Scripts index** (CI gates / generators / QA): [`scripts/README.md`](scripts/README.md)
- **Release notes**: [`CHANGELOG.md`](CHANGELOG.md) · VS Code marketplace listing: [`packages/vscode/CHANGELOG.md`](packages/vscode/CHANGELOG.md)
- **Contributing**: [`CONTRIBUTING.md`](.github/CONTRIBUTING.md) · [`CODE_OF_CONDUCT.md`](.github/CODE_OF_CONDUCT.md)
- **API docs index**: [`docs/api/index.md`](docs/api/index.md)
- **API docs (简体中文)**: [`docs/api.zh-CN/index.md`](docs/api.zh-CN/index.md)
- **MCP tool reference**: [`docs/mcp_tools.md`](docs/mcp_tools.md)
- **MCP 工具说明**: [`docs/mcp_tools.zh-CN.md`](docs/mcp_tools.zh-CN.md)
- **Troubleshooting / FAQ**: [`docs/troubleshooting.md`](docs/troubleshooting.md) · [`docs/troubleshooting.zh-CN.md`](docs/troubleshooting.zh-CN.md)
- **Release recovery runbook**: [`docs/release-recovery.md`](docs/release-recovery.md) · [`docs/release-recovery.zh-CN.md`](docs/release-recovery.zh-CN.md)
- **i18n contributor guide**: [`docs/i18n.md`](docs/i18n.md)
- **DeepWiki Q&A** — AI-augmented Q&A over the repo: <a href="https://deepwiki.com/xiadengma/ai-intervention-agent"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki" valign="middle" /></a>

## Related projects

- [interactive-feedback-mcp](https://github.com/poliva/interactive-feedback-mcp)
- [mcp-feedback-enhanced](https://github.com/Minidoracat/mcp-feedback-enhanced)
- [cunzhi](https://github.com/imhuso/cunzhi)
- [other interactive-feedback-mcp](https://github.com/Pursue-LLL/interactive-feedback-mcp)

## Acknowledgements

This project's heritage traces back to **Fábio Ferreira** (2024) and **Pau Oliva** (2025), whose original [`noopstudios/interactive-feedback-mcp`](https://github.com/noopstudios/interactive-feedback-mcp) and [`poliva/interactive-feedback-mcp`](https://github.com/poliva/interactive-feedback-mcp) seeded the MCP `interactive_feedback` tool surface. Their copyright notices are preserved in [`LICENSE`](LICENSE) per the MIT license terms. The v1.5.x line is a substantial rewrite — Web UI, VS Code extension, i18n, notification stack, CI/CD pipeline — owned and maintained by [@xiadengma](https://github.com/xiadengma) (PyPI / Open VSX / VS Code Marketplace publisher).

## License

MIT License
