User feedback widget + MCP server for AI coding agents. One command to install.
<p align="center">
<picture>
<source media="(prefers-color-scheme: dark)" srcset=".github/assets/logo-light.svg" />
<source media="(prefers-color-scheme: light)" srcset=".github/assets/logo-dark.svg" />
<img alt="UserDispatch" src=".github/assets/logo-dark.svg" width="80" />
</picture>
</p>
<h3 align="center">UserDispatch <sup><img src="https://img.shields.io/badge/beta-blue" alt="beta" /></sup></h3>
<p align="center">
<a href="https://www.npmjs.com/package/userdispatch"><img src="https://img.shields.io/npm/v/userdispatch?color=blue" alt="npm version" /></a>
<a href="https://www.npmjs.com/package/userdispatch"><img src="https://img.shields.io/npm/dm/userdispatch?color=blue" alt="npm downloads" /></a>
<a href="https://userdispatch.com"><img src="https://img.shields.io/badge/website-userdispatch.com-blue" alt="website" /></a>
<a href="https://userdispatch.com/docs"><img src="https://img.shields.io/badge/docs-userdispatch.com%2Fdocs-blue" alt="docs" /></a>
<a href="./LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue" alt="license" /></a>
</p>
<p align="center">
Add a feedback widget to any web app in one command.<br />
Your AI coding agent triages feedback, drafts PRs, and responds to users — via MCP.
</p>
<p align="center">
<img src=".github/assets/og-image.png" alt="UserDispatch — feedback widget + MCP server for AI coding agents" width="720" />
</p>
---
## Quick start
```bash
npx userdispatch init
```
One command does everything:
- **Installs a feedback widget** in your app (auto-detects framework)
- **Creates your org & app** on userdispatch.com
- **Configures your AI coding agent** with the MCP server
- **Sends a test submission** to verify the full loop
Requires Node.js 18+. Full CLI reference: [userdispatch.com/docs/cli](https://userdispatch.com/docs/cli)
## How it works
```
┌─────────────┐ ┌──────────────────┐ ┌─────────────────┐ ┌──────────────┐
│ 1. User │────▶│ 2. Agent reads │───Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.