AI Intervention Agent monorepo root: aggregates the PyPI MCP server, the VS Code / Open VSX extension under packages/vscode, and Web UI tooling.
If you already use Ai Intervention Agent, the ai intervention agent mcp server is the piece that lets your assistant work with it directly. AI Intervention Agent monorepo root: aggregates the PyPI MCP server, the VS Code / Open VSX extension under packages/vscode, and Web UI tooling. private:true; never published to npm.
Real-time user intervention for MCP agents — pause, course-correct, resume.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
command — uvxargs — ["ai-intervention-agent"]timeout — 600autoApprove — ["interactive_feedback"]Real — time intervention** — the agent pauses and waits for your input via interactive_feedbackMulti — task tabs** — concurrent requests with independent countdowns, per-task draft autosave, and auto re-submit that keeps long sessions alive (your typedTyping-hold — the countdown auto-extends while you type and never fires mid-input (web page and VS Code extension alike)Agent — loop ergonomics** — per-task header_label context chips, question_type='yesno' one-click decisions, and feedback_placeholder hintsNotifications — web / sound / system / Bark (iOS push), plus custom notification sound uploadi18n — Web UI + VS Code extension shipped in en / zh-CN / zh-TWMore — ai-intervention-agent.logLevel, macOS native notifications (on by default, toggle in the sidebar's Notification Settings panel) — full settings listContributing — CONTRIBUTING.md · CODE_OF_CONDUCT.md · scripts index: scripts/README.mdConfiguration is passed through the environment: AI_INTERVENTION_AGENT_WEB_UI_HOST, AI_INTERVENTION_AGENT_WEB_UI_PORT, AI_INTERVENTION_AGENT_WEB_UI_LANGUAGE. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
The server ships on PyPI as ai-intervention-agent, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Ai Intervention Agent's toolset — command, args, timeout and 11 more — is a fair guide to whether it matches your workflow. It is maintained by XIADENGMA; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Ai Intervention Agent's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| command | uvx |
| args | ["ai-intervention-agent"] |
| timeout | 600 |
| autoApprove | ["interactive_feedback"] |
| Real | time intervention** — the agent pauses and waits for your input via interactive_feedback |
| Multi | task tabs** — concurrent requests with independent countdowns, per-task draft autosave, and auto re-submit that keeps long sessions alive (your typed text and checked options are submitted at zero, never an empty prompt) |
| Typing-hold | the countdown auto-extends while you type and never fires mid-input (web page and VS Code extension alike) |
| Agent | loop ergonomics** — per-task header_label context chips, question_type='yesno' one-click decisions, and feedback_placeholder hints |
| Notifications | web / sound / system / Bark (iOS push), plus custom notification sound upload |
| i18n | Web UI + VS Code extension shipped in en / zh-CN / zh-TW |
| More | ai-intervention-agent.logLevel, macOS native notifications (on by default, toggle in the sidebar's Notification Settings panel) — full settings list and the AppleScript executor security model in [packages/vscode/README. |
| Contributing | [CONTRIBUTING.md](.github/CONTRIBUTING.md) · [CODE_OF_CONDUCT.md](.github/CODE_OF_CONDUCT.md) · scripts index: [scripts/README.md](scripts/README.md) · i18n guide: [docs/i18n.md](docs/i18n.md) |
| Linux | ~/.config/ai-intervention-agent/ |
| macOS | ~/Library/Application Support/ai-intervention-agent/ |
{
"mcpServers": {
"ai-intervention-agent": {
"command": "uvx",
"args": ["ai-intervention-agent"],
"timeout": 600,
"autoApprove": ["interactive_feedback"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| AI_INTERVENTION_AGENT_WEB_UI_HOST | Endpoint or connection string the server talks to. | Optional |
| AI_INTERVENTION_AGENT_WEB_UI_PORT | Configuration value read at startup. | Optional |
| AI_INTERVENTION_AGENT_WEB_UI_LANGUAGE | Configuration value read at startup. | Optional |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.