mcp-console-hub
Streams browser DevTools console, network, storage, and performance data to your IDE's AI agent for real-time debugging and analysis.
README
<div align="center"> <img src="assets/logo.svg" alt="MCP Console Hub" width="120" height="120"> <h1>mcp-console-hub</h1> <p><strong>Your browser's DevTools, streamed to your IDE's AI agent.</strong></p> <p> <a href="https://www.npmjs.com/package/mcp-console-hub"><img src="https://img.shields.io/npm/v/mcp-console-hub?style=flat-square&color=06b6d4" alt="npm"></a> <a href="https://www.npmjs.com/package/mcp-console-hub"><img src="https://img.shields.io/npm/dm/mcp-console-hub?style=flat-square&color=06b6d4" alt="downloads"></a> <a href="https://modelcontextprotocol.io"><img src="https://img.shields.io/badge/MCP-Compatible-blue?style=flat-square" alt="MCP"></a> <a href="https://nodejs.org"><img src="https://img.shields.io/badge/Node.js-20%2B-green?style=flat-square" alt="Node"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow?style=flat-square" alt="License"></a> </p> </div>
What It Captures
| DevTools Tab | What's Captured | Details |
|---|---|---|
| Console | console.error/warn/log/info/debug |
With stack traces for errors/warnings |
| Console | Unhandled exceptions | window.onerror with file + line + column |
| Console | Promise rejections | unhandledrejection with stack |
| Network | All fetch/XHR requests | Method, URL, status, duration, headers, body preview, size |
| Network | Failed requests | 4xx, 5xx, connection errors with details |
| Application | localStorage | All key-value pairs |
| Application | sessionStorage | All key-value pairs |
| Application | Cookies | Name, value, domain, path |
| Application | IndexedDB | Database names |
| Performance | Navigation timing | TTFB, DOM loaded, load complete, DNS, connect |
| Performance | Resource loading | JS, CSS, images, fonts with duration + size |
| Performance | Memory | Heap size (Chrome only) |
| Performance | Marks & Measures | Custom performance marks |
Zero code changes. One bookmarklet. Works with any web app.
Quick Start
1. Configure your IDE
<details> <summary><strong>Cursor</strong></summary>
{
"mcpServers": {
"mcp-console-hub": {
"command": "npx",
"args": ["-y", "mcp-console-hub@latest"]
}
}
}
</details>
<details> <summary><strong>VSCode</strong></summary>
{
"servers": {
"mcp-console-hub": {
"type": "stdio",
"command": "npx",
"args": ["-y", "mcp-console-hub@latest"]
}
}
}
</details>
<details> <summary><strong>Claude Code</strong></summary>
claude mcp add mcp-console-hub npx -y mcp-console-hub@latest
</details>
<details> <summary><strong>Antigravity / Windsurf / OpenCode</strong></summary>
{
"mcpServers": {
"mcp-console-hub": {
"command": "npx",
"args": ["-y", "mcp-console-hub@latest"]
}
}
}
</details>
2. Connect your browser
Open http://localhost:3200 — drag the bookmarklet to your bookmarks bar.
Navigate to any web app. Click the bookmarklet.
3. Ask your AI agent
@mcp-console-hub Diagnose all errors and suggest fixes
@mcp-console-hub Show all network failures
@mcp-console-hub Read localStorage and explain the app state
@mcp-console-hub Audit page performance
@mcp-console-hub Fix errors by priority — most critical first
MCP Tools (24 tools)
Console (7 tools)
| Tool | Description |
|---|---|
query_console |
Filter by level, source, text, time, stack |
get_entry_context |
Full context with parsed stack frames + timeline |
get_error_chains |
Detect cascading errors (root cause analysis) |
get_repeated_patterns |
Find recurring messages |
parse_stack_trace |
Structured frames: function, file, line, col |
find_by_file |
Find all errors from a specific source file |
get_unhandled_errors |
Runtime exceptions + promise rejections |
Network (4 tools)
| Tool | Description |
|---|---|
query_network |
Filter by method, status, URL, duration |
get_network_detail |
Full request/response: headers, body, timing |
get_network_errors |
All 4xx, 5xx, and connection failures |
get_slow_requests |
Requests above duration threshold |
Storage (3 tools)
| Tool | Description |
|---|---|
read_storage |
All storage: localStorage, sessionStorage, cookies, IndexedDB |
read_storage_key |
Read specific key with auto JSON parse |
get_cookies |
List/search cookies |
Performance (2 tools)
| Tool | Description |
|---|---|
get_performance |
Navigation timing, resources, memory, marks |
get_slow_resources |
Find slow-loading JS, CSS, images, fonts |
General (4 tools)
| Tool | Description |
|---|---|
get_console_stats |
Aggregated statistics |
get_page_info |
Page URL, user agent, all data availability |
get_timeline |
Chronological event sequence |
clear_console |
Clear all captured data |
Export (1 tool)
| Tool | Description |
|---|---|
export_report |
Full DevTools report as JSON or Markdown |
MCP Prompts (7 prompts)
| Prompt | Trigger | Description |
|---|---|---|
diagnose |
/diagnose |
Full analysis of errors + network + performance |
fix_by_priority |
/fix_by_priority |
Prioritized fix list: Critical > High > Medium |
suggest_solution |
/suggest_solution |
Concrete code fix for the most recent error |
debug_network |
/debug_network |
Analyze failures, CORS issues, auth errors |
read_app_state |
/read_app_state |
Analyze storage to understand app state |
performance_audit |
/performance_audit |
Page load audit with optimization suggestions |
fix_entry |
/fix_entry |
Step-by-step fix for the latest error |
MCP Resources (12 resources)
| URI | Description |
|---|---|
console://entries |
All console entries |
console://errors |
Error-level only |
console://warnings |
Warning-level only |
console://timeline |
Chronological timeline |
console://summary |
Aggregated stats |
network://requests |
All network requests |
network://errors |
Failed requests |
network://slow |
Slow requests (>1s) |
storage://snapshot |
Full storage snapshot |
storage://cookies |
Cookies only |
performance://data |
All performance data |
devtools://page |
Page info + data availability |
How It Works
Browser (any web app) MCP Console Hub IDE AI Agent
+-----------------+ +--------------------+ +----------------+
| Bookmarklet | WebSocket | | stdio | |
| captures: |==============>| Console Store |<===========>| 24 MCP Tools |
| | :3201 | Network Store | | 12 Resources |
| - console.* | | Storage Snapshot | | 7 Prompts |
| - window.onerror| HTTP POST | Performance Data | | |
| - fetch/XHR |-------------->| | | Cursor |
| - localStorage | :3200 | File-backed | | VSCode |
| - cookies | | (.store/) | | Claude Code |
| - performance | | | | Antigravity |
+-----------------+ +--------------------+ +----------------+
zero code changes npx mcp-console-hub IDE MCP config
Ports & Environment
| Port | Protocol | Purpose |
|---|---|---|
| 3200 | HTTP | Connector page + health + ingestion |
| 3201 | WebSocket | Real-time data streaming |
| Variable | Default | Description |
|---|---|---|
MCP_CONSOLE_HUB_PORT |
3200 |
HTTP port |
MCP_CONSOLE_HUB_WS_PORT |
3201 |
WebSocket port |
MCP_CONSOLE_HUB_STORE_PATH |
auto | Custom store file path |
License
MIT — see LICENSE
<div align="center"> <sub>Built by <a href="https://github.com/nano-step"><strong>nano-step</strong></a> — Copyright © 2026 Hoai Nho Nguyen</sub> </div>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.