NestJS DevTools MCP
Give your AI coding agents the superpower to observe your NestJS application's runtime state in real-time.
README
NestJS DevTools MCP
Give your AI coding agents (Claude, Cursor, Copilot) the superpower to observe your NestJS application's runtime state in real-time.
Ever wished AI could see your crashed application logs, registered routes, or current DI container without you copy-pasting terminal outputs? This project provides a transparent, near-zero config bridge between your running NestJS app and your AI tools via the Model Context Protocol (MCP).
Current MCP Tools
Currently available tools:
discover_servers— Find local NestJS servers with the plugin enabled.get_logs— Retrieve recent runtime logs from a detected NestJS server.get_routes— List registered HTTP routes (method, path, controller, handler).get_request_history— Retrieve recent HTTP request history with filters for method, status, path, duration, and errors.get_config— Retrieve sanitized runtime configuration from environment variables and ConfigService.
get_request_history captures real HTTP traffic, including unmatched 404s, without recording request or response bodies by default. Internal /_dev/mcp/* calls are excluded so tool calls do not pollute the history.
get_config is read-only and always masks values that look sensitive, including tokens, passwords, auth keys, private keys, and database URLs. Secret masking cannot be disabled.
More tools may be added in future releases.
Quick Start (2 Steps)
Step 1: Integrate Plugin into NestJS
Install the plugin package in your NestJS application:
# Using npm
npm install @nestjs-devtools-mcp/plugin
# Using yarn
yarn add @nestjs-devtools-mcp/plugin
# Using pnpm
pnpm add @nestjs-devtools-mcp/plugin
Configure app.module.ts:
import { Module } from '@nestjs/common'
import { DevtoolsMcpModule } from '@nestjs-devtools-mcp/plugin'
@Module({
imports: [
DevtoolsMcpModule.register(), // Automatically disables in production
],
})
export class AppModule {}
Request body capture is off by default. If you need it for local debugging, enable DevtoolsMcpModule.register({ captureRequestBody: true }); multipart bodies are never captured, and configuration secrets returned by get_config are always masked.
Apply the custom logger in main.ts to allow context interception:
import { NestFactory } from '@nestjs/core'
import { AppModule } from './app.module'
import { applyDevtoolsLogger } from '@nestjs-devtools-mcp/plugin'
async function bootstrap() {
const app = await NestFactory.create(AppModule, {
bufferLogs: true,
})
// Activate DevTools logger
applyDevtoolsLogger(app)
await app.listen(3000)
}
bootstrap()
Step 2: Configure MCP Client
Add the following to your AI Assistant's MCP settings (e.g., claude_desktop_config.json):
{
"mcpServers": {
"nestjs-devtools": {
"command": "npx",
"args": ["-y", "nestjs-devtools-mcp@latest"]
}
}
}
That's it! Restart your MCP client and ask your AI: "Fetch the latest logs from my NestJS application."
Documentation & Guides
Looking for advanced setups or want to contribute? Dive deeper into our docs:
- Installation & Usage Guide - Advanced setups, installing from source, and troubleshooting.
- Development Guide - For contributors, detailing the monorepo setup, building, testing, and linting.
- API Specs - The MCP protocol specification and contract.
How it Works (Architecture)
The project uses a secure 2-package model to avoid interfering with your app's logic:
AI Client (Claude, Cursor, ...)
│
│ [STDIO - MCP Protocol]
▼
nestjs-devtools-mcp (Bridge Server via npx)
│
│ [HTTP - Localhost Only]
▼
@nestjs-devtools-mcp/plugin (Runs inside your App)
│
▼
NestJS Runtime (Logger, Container, Routes)
- The Plugin (
@nestjs-devtools-mcp/plugin) runs inside your NestJS process, safely collecting runtime data into circular buffers and exposing an internal HTTP endpoint. - The Server (
nestjs-devtools-mcp) is a lightweight Bridge CLI that manages STDIO communication with the AI and proxies tool calls over HTTP to the plugin.
License
MIT © HaoNgo232. For production environments, always reassess security assumptions before deploying plugins that observe application state.
Marketplace Ownership Verification
To improve trust signals in LobeHub MCP Marketplace and verify ownership:
- Keep the MCP badge in this README (already added above).
- Open your listing page: https://lobehub.com/mcp/hao%20ngo232-nestjs-devtools-mcp.
- Use the "Check Claim Status" flow and complete GitHub ownership verification.
After LobeHub re-crawls the repository, the owner claim status should be updated on the score page.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。