pulse-mcp-bridge

pulse-mcp-bridge

Bridges your IDE to a running React Native/Expo mobile app over local Wi-Fi, providing live device status, app logs, and a combined standup snapshot.

Category
访问服务器

README

pulse-mcp-bridge

An MCP (Model Context Protocol) server that bridges your IDE to a running React Native / Expo mobile app on your local Wi-Fi network, so tools like Claude Code or Cursor can pull live device status, app logs, and a combined standup snapshot (device status + today's git commits).

How it fits together

IDE (MCP client) <--stdio--> pulse-mcp (index.js) <--HTTP--> mobile app (mobile-app-server.js)
                                                         or  <--HTTP--> mock-phone.js (for local testing)

Setup

npm install

1. Try it locally with the mock phone (no device needed)

In one terminal, start the mock phone server:

node mock-phone.js

This listens on http://localhost:8080 and fakes /status and /logs responses.

2. Register the MCP server with your IDE

See mcp-config.example.json for ready-to-paste config blocks for Cursor, Claude Desktop, and Windsurf. Point MOBILE_PHONE_IP at:

  • 127.0.0.1 when testing against mock-phone.js
  • your phone's local IP (e.g. 192.168.1.50) when testing against a real device

3. Wire up the real mobile app

Copy mobile-app-server.js into your React Native / Expo app (e.g. src/pulseServer.js) and follow the integration comments at the top of the file:

npm install react-native-http-bridge-refurbished react-native-device-info react-native-view-shot

Then in App.tsx:

import { startPulseServer, setCurrentRoute, recordLog } from "./pulseServer";

useEffect(() => {
  if (__DEV__) startPulseServer();
}, []);

// Anywhere in the app:
recordLog("Synced dashboard data", "success", "SyncService");
recordLog(`Network request failed: ${error.message}`, "error", "NetworkClient");

Make sure your phone and dev machine are on the same Wi-Fi network.

Verified: this integration has been tested end-to-end against a real Expo/React Native app running on the iOS Simulator (Expo SDK 51 / RN 0.74), including a live crash scenario — the bridge correctly goes unreachable when the app stops responding. Android has not been tested yet.

Available MCP tools

Tool Description
get_mobile_device_status Battery level, active route/screen, OS/platform, and connectedAt from the running app
get_mobile_app_logs Recent structured log entries ({ id, timestamp, level, source, message, device }) captured in the app; optionally filter by level (info/success/error)
check_mobile_connection Pings /status and returns a friendly human-readable connection summary plus the raw status JSON, or a clean unreachable error
diagnose_mobile_error Finds the most recent error-level log and returns a structured diagnosis (likelyCause/suggestion) derived from the message text
get_standup_snapshot Combines live device status with today's local git commits (falls back gracefully outside a git repo)
get_mobile_screenshot Live screenshot of whatever screen is currently showing on the app, returned as an inline image
get_bug_report The current/live step recording (see below) plus device context, for reproducing a bug in progress
get_saved_bug_reports All bug reports auto-saved on the device, each with its full steps, logs, and device info snapshot

Bug-report step recording

Wire a "Start/Stop Recording" toggle in your app to startSessionRecording() / stopSessionRecording(), and call recordStep(...) at any point worth capturing (button taps, network results, errors). When recording stops, a complete report — numbered steps, full logs, and a device/build info snapshot — is auto-saved and instantly queryable via get_bug_report / get_saved_bug_reports. No manual "steps to reproduce" writeup needed.

Environment variables

Variable Default Purpose
MOBILE_PHONE_IP 192.168.1.50 IP address of the phone/mock server running the HTTP bridge

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选