Install
$ agentstack add mcp-mcpc-tech-dev-inspector-mcp Open-source listing — not yet scanned by AgentStack. Follow the source repository for install instructions.
Security review
⚠ Flagged1 finding(s); flagged for manual review. · v0.1.0 How review works →
- • Prompt-injection patterns
- • Secret / credential exfiltration
- • Dangerous shell & filesystem operations
- • Untrusted network calls
- • Known-malicious package signatures
- high Pipes remote content directly into a shell (remote code execution).
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ● Environment & secrets Used
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
dev-inspector-mcp
[](https://www.npmjs.com/package/@mcpc-tech/unplugin-dev-inspector-mcp) [](https://www.npmjs.com/package/@mcpc-tech/unplugin-dev-inspector-mcp)
The missing runtime context for AI coding agents.
AI can read your code, but can't see what's happening at runtime. DevInspector provides the missing context: source code location, DOM state, styles, network, console, terminal output, and screenshots.
Two modes: Use with your IDE's AI (Cursor, VSCode) via MCP, or run AI agents directly in the browser via ACP (Claude Code, Codex CLI, Gemini CLI, OpenCode, more).
> Using Claude Code or another AI agent? Install the DevInspector skill so your agent knows how to set up and troubleshoot the inspector: > > ``bash > npx skills add mcpc-tech/dev-inspector-mcp > ``
Table of Contents
- [Demo Video](#demo-video)
- [Social Media](#social-media)
- [Key Features](#key-features)
- [Quick Start](#quick-start)
- [Installation](#installation)
- [Automated Setup](#automated-setup-recommended)
- [Framework Setup](#framework-setup)
- [Agent Skills](#agent-skills)
- [Configuration](#configuration)
- [Auto-Update MCP Config](#auto-update-mcp-config)
- [Agent Installation](#agent-installation)
- [Custom Agents](#custom-agents)
- [MCP Servers Configuration](#mcp-servers-configuration)
- [What It Does](#what-it-does)
- [Two Workflow Modes](#two-workflow-modes)
- [MCP Tools](#mcp-tools)
- [Custom Inspector Tools](#custom-inspector-tools)
- [MCP Prompts](#mcp-prompts)
- [Architecture](#architecture)
Demo Video
Watch the demo: https://www.youtube.com/shorts/TCt2oOtPS_k
Social Media
Twittter/X Post: https://x.com/yaoandyan/status/1995082020431753600
Key Features
Visual Context & Region Selection
Click any element to inspect it, or drag to select a region. AI gets the full context: source code location, computed styles, component hierarchy, IDs, classes, text content, and automatically captures screenshots for pixel-perfect visual understanding.
Page Overview & Accessibility Tree
get_page_info provides AI with a semantic understanding of the page: URL, viewport, and an accessibility tree showing landmarks, headings, forms, and links. AI can navigate the page structure without screenshots.
Universal DevTools Access
AI can access Network and Console logs from any browser (via client-side interception) or full Chrome DevTools (via chrome devtools mcp). It sees what you see, regardless of your environment.
Multi-Agent Workflow
Switch between agents (Claude Code, Codex, Gemini, Opencode...) and track their debugging progress visually with a floating status bar.
Quick Start
Installation
# npm - basic installation
npm i -D @mcpc-tech/unplugin-dev-inspector-mcp
# pnpm - basic installation
pnpm add -D @mcpc-tech/unplugin-dev-inspector-mcp
# yarn - basic installation
yarn add -D @mcpc-tech/unplugin-dev-inspector-mcp
> Note: If you don't need the ACP agents (Inspector Bar mode), add --no-optional to skip installing agent packages: > > ``bash > npm i -D @mcpc-tech/unplugin-dev-inspector-mcp --no-optional > pnpm add -D @mcpc-tech/unplugin-dev-inspector-mcp --no-optional > yarn add -D @mcpc-tech/unplugin-dev-inspector-mcp --no-optional > ``
Automated Setup (Recommended)
Run the setup command to automatically configure your vite.config.ts, webpack.config.js, or next.config.ts:
npx @mcpc-tech/unplugin-dev-inspector-mcp setup
Options:
--dry-run- Preview changes without applying them--config- Specify config file path (auto-detect by default)--bundler- Specify bundler type: vite, webpack, nextjs--no-backup- Skip creating backup files--help- Show help message
Examples:
# Preview changes before applying
npx @mcpc-tech/unplugin-dev-inspector-mcp setup --dry-run
# Setup specific config file
npx @mcpc-tech/unplugin-dev-inspector-mcp setup --config vite.config.ts
# Setup for specific bundler
npx @mcpc-tech/unplugin-dev-inspector-mcp setup --bundler vite
This will:
- Detect your bundler configuration
- Add the necessary import
- Add the plugin to your configuration
- Create a backup of your config file
Framework Setup
Pick your framework below. Each section is self-contained -- just copy the config.
Vite (React / Vue / Svelte / Solid / Preact)
// vite.config.ts
import DevInspector from '@mcpc-tech/unplugin-dev-inspector-mcp';
import react from '@vitejs/plugin-react'; // or vue(), svelte(), solid(), preact()
export default {
plugins: [
DevInspector.vite({ enabled: true }),
react(),
],
};
> Plugin order matters: Place DevInspector.vite() before framework plugins. Otherwise source locations may show unknown:0:0.
Next.js (Webpack + Turbopack)
Step 1 -- next.config.ts:
import DevInspector, { turbopackDevInspector } from '@mcpc-tech/unplugin-dev-inspector-mcp';
const nextConfig = {
webpack: (config) => {
config.plugins.push(DevInspector.webpack({ enabled: true }));
return config;
},
turbopack: {
rules: turbopackDevInspector({ enabled: true }),
},
};
export default nextConfig;
Step 2 -- app/layout.tsx (required):
import { DevInspector } from "@mcpc-tech/unplugin-dev-inspector-mcp/next";
export default function RootLayout({ children }) {
return (
{children}
);
}
Run with next dev (webpack) or next dev --turbopack (turbopack).
React Router v7+ (Remix)
// vite.config.ts
import { reactRouter } from "@react-router/dev/vite";
import DevInspector from '@mcpc-tech/unplugin-dev-inspector-mcp';
export default defineConfig({
plugins: [
DevInspector.vite({ enabled: true, entry: "app/root.tsx" }),
reactRouter(),
],
});
Webpack (standalone)
// webpack.config.js
const DevInspector = require('@mcpc-tech/unplugin-dev-inspector-mcp');
module.exports = {
plugins: [
DevInspector.webpack({ enabled: true }),
],
};
Advanced options
Non-HTML Projects (Miniapps, Library Bundles)
DevInspector.vite({
enabled: true,
autoInject: false,
entry: 'src/main.ts',
})
TypeScript Types
If you import virtual:dev-inspector-mcp, add to your tsconfig:
{
"compilerOptions": {
"types": ["vite/client", "@mcpc-tech/unplugin-dev-inspector-mcp/client"]
}
}
Custom Virtual Module Name
DevInspector.vite({
enabled: true,
autoInject: false,
virtualModuleName: 'virtual:my-custom-inspector',
})
Disable Chrome DevTools
Set disableChrome: true in plugin options or DEV_INSPECTOR_DISABLE_CHROME=1 env var.
Zero Production Impact: In production builds, virtual:dev-inspector-mcp becomes a no-op module.
Supported Frameworks
React, Vue, Svelte, SolidJS, Preact, Next.js (Webpack + Turbopack), React Router v7+. Angular support in progress.
Agent Skills
DevInspector ships a built-in Agent Skill for Claude Code (and compatible AI agents) that teaches the agent how to integrate and troubleshoot the inspector.
Install it with one command:
npx skills add mcpc-tech/dev-inspector-mcp
The skill covers setup for all supported bundlers, common gotchas, and troubleshooting -- so the agent can guide you through the entire integration without back-and-forth.
> What are Agent Skills? Skills are Markdown-based instruction sets that AI agents load at session start to gain domain-specific knowledge. See the Claude Code docs for more.
Configuration
Auto-Update MCP Config
The plugin automatically updates MCP configuration files for detected editors when the dev server starts. This saves you from manually configuring MCP endpoints.
Supported editors: Cursor, VSCode, Windsurf, Claude Code, Antigravity
// vite.config.ts
DevInspector.vite({
// Auto-detect and update (default: true)
updateConfig: true,
// Or specify editors manually
updateConfig: ['cursor', 'vscode'],
// Or disable
updateConfig: false,
// Server name in MCP config (default: 'dev-inspector')
updateConfigServerName: 'my-app-inspector',
})
Custom editors: For non-standard editors, use customEditors:
DevInspector.vite({
customEditors: [
{
id: 'my-editor',
name: 'My Editor',
configPath: '~/.my-editor', // absolute, ~/relative, or project-relative
configFileName: 'mcp.json',
serverUrlKey: 'url', // default: 'url'
configFormat: 'mcpServers', // 'mcpServers' or 'servers' (vscode-style)
},
],
})
Agent Installation
DevInspector supports multiple AI agents via ACP.
For npm-based agents (Claude Code, Codex CLI, Cursor Agent, Droid), you can pre-install them as dev dependencies for faster loading.
For system-level agents, install globally:
Gemini CLI
npm install -g @google/gemini-cli
Kimi CLI
uv tool install --python 3.13 kimi-cli
Goose
pipx install goose-ai
Opencode
curl -fsSL https://opencode.ai/install | bash
CodeBuddy Code
npm install -g @tencent-ai/codebuddy-code
> Note: If you don't pre-install npm-based agents, they will be launched via npx on first use (slower startup).
Pre-installing npm-based Agents (Recommended)
The recommended way is to install agents during initial setup (see [Installation](#installation) above).
Alternatively, install them later as dev dependencies:
# npm
npm i -D @zed-industries/claude-code-acp
# pnpm
pnpm add -D @zed-industries/claude-code-acp
# Or add directly to package.json
{
"devDependencies": {
"@zed-industries/claude-code-acp": "^0.12.4",
"@zed-industries/codex-acp": "^0.7.1",
"@blowmage/cursor-agent-acp": "^0.1.0",
"@yaonyan/droid-acp": "^0.0.8"
}
}
> About optionalDependencies: Agent packages are installed by default. If you don't need them, use --no-optional when installing.
Why install as devDependencies?
- Ensures faster startup (uses local package via
require.resolveinstead ofnpx) - Won't affect production bundle (tree-shaken out unless imported)
- Standard practice for development tools
Custom Agents
This plugin uses the Agent Client Protocol (ACP) to connect with AI agents.
⏱️ Note: Initial connection may be slow as agents are launched via npx (downloads packages on first run).
Default agents: View configuration →
You can customize available AI agents, filter visible agents, and set a default agent:
// vite.config.ts
export default {
plugins: [
DevInspector.vite({
enabled: true,
// Option 1: Only show specific agents (filters merged agents)
visibleAgents: ['Claude Code', 'Gemini CLI', 'Goose'],
// Option 2: Add custom agents (merges with defaults)
agents: [
{
name: "Claude Code", // Matches default - auto-fills icon and env
command: "npx",
args: ["-y", "@zed-industries/claude-code-acp"],
},
{
name: "My Custom Agent",
command: "my-agent-cli",
args: ["--mode", "acp"],
env: [{ key: "MY_API_KEY", required: true }],
meta: { icon: "https://example.com/icon.svg" }
}
],
// Option 3: Combine both - add custom agents and filter visibility
agents: [
{
name: "My Custom Agent",
command: "my-agent-cli",
args: ["--mode", "acp"],
env: [{ key: "MY_API_KEY", required: true }],
meta: { icon: "https://example.com/icon.svg" }
}
],
visibleAgents: ['Claude Code', 'My Custom Agent'], // Only show these
// Set default agent to show on startup
defaultAgent: "Claude Code"
}),
],
};
Key Features:
agents: Merges your custom agents with defaults. Agents with the same name as default agents automatically inherit missing properties (icons, env)visibleAgents: Filters which agents appear in the UI (applies after merging). Great for limiting options to only what your team usesdefaultAgent: Sets which agent is selected on startup- If no custom agents provided, defaults are: Claude Code, Codex CLI, Gemini CLI, Kimi CLI, Goose, Opencode, Cursor Agent, Droid, CodeBuddy Code
MCP Servers Configuration
You can configure external MCP servers for agents to access additional tools.
DevInspector.vite({
mcpServers: [
// HTTP/SSE Server
{
name: 'remote-server',
type: 'sse', // or 'http'
url: 'https://api.example.com/sse',
headers: [{ name: 'Authorization', value: process.env.MCP_TOKEN ?? '' }]
},
// Local Stdio Server
{
name: 'local-server',
command: 'npx',
args: ['-y', '@modelcontextprotocol/server-memory'],
env: { MY_VAR: 'value' }
}
]
})
What It Does
Click element → Describe issue → AI analyzes → Get fix
- Click any UI element to capture context (source, styles, DOM)
- Describe what's wrong or ask a question about the element
- AI diagnoses using Chrome DevTools integration
- Get intelligent solutions through natural conversation
Examples:
- "Why is this button not clickable?" → AI checks
pointer-events, z-index, overlays - "This API call is failing" → AI analyzes network requests, timing, responses
- "Where is this component?" → Jump to source file and line number
Two Workflow Modes
DevInspector offers two ways to interact with your AI, depending on your preference:
1. Editor Mode
Best for: Code-heavy tasks, refactoring, and maintaining flow.
- How it works: You use your IDE's AI assistant (Cursor, Windsurf, Copilot).
- The Flow: Click an element in the browser -> The context (source, props, styles) is sent to your Editor via MCP -> You ask your Editor to fix it.
- Why: Keeps you in your coding environment.
2. Inspector Bar Mode (Recommended)
Best for: Quick fixes, visual tweaks, or if you don't use an AI editor.
- How it works: You use the floating "Inspector Bar" directly in the browser.
- The Flow: Click "Ask AI" in the browser -> Select an agent (e.g., Claude Code, Custom Script) -> The agent runs in your terminal but interacts with the browser overlay.
- Why: No context switching. Great for "what is this?" questions or network debugging.
MCP Tools
capture_element_context
Capture single element context. Two modes:
- Interactive (default): User clicks element to select
- Automated: Use
selectorparam for programmatic capture
Returns: source location, DOM hierarchy, computed styles, dimensions, user notes, screenshot.
capture_area_context
Capture multiple elements in an area. Two modes:
- Interactive (default): User draws rectangle to select area
- Automated: Use
containerSelectororboundsparam
Returns: array of element contexts (max 50).
get_page_info
Get page overview with accessibility tree. Returns URL, title, viewport, document size, and semantic structure (landmarks, headings, fo
…
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: mcpc-tech
- Source: mcpc-tech/dev-inspector-mcp
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.