# PluggedIn — MCP Proxy + Server Manager UI
> Self-hostable AI CMS with RAG and an MCP server hub. Turn chats into versioned knowledge; manage MCP integrations. Verified 94★; pushed 2026-05-14.
## Install
Merge the JSON below into your `.mcp.json`:
## Quick Use
```bash
git clone https://github.com/VeriTeknik/pluggedin-app.git
cd pluggedin-app
cp .env.example .env
docker compose up --build -d
open http://localhost:12005
```
## Intro
Self-hostable AI CMS with RAG and an MCP server hub. Turn chats into versioned knowledge; manage MCP integrations. Verified 94★; pushed 2026-05-14.
**Best for:** Teams who want an internal AI knowledge hub plus a UI to discover and configure MCP servers
**Works with:** Docker Compose; Next.js app + Postgres/pgvector; MCP server hub (README)
**Setup time:** 10-20 minutes
### Key facts (verified)
- GitHub: 94 stars · 15 forks · pushed 2026-05-14.
- License: MIT · owner avatar + repo URL verified via GitHub API.
- README-backed entrypoint: `docker compose`.
## Main
- Treat it like “Git for AI content”: version conversation outputs, attribute changes, and keep an audit trail for teams.
- Use the MCP hub to standardize server onboarding: one place to discover, configure, and namespace tools.
- Start self-hosted with Docker Compose, then decide if you need external vector infra—the README also highlights embedded options.
- For security, keep tokens/API keys in env vars and rotate them just like any internal platform credential.
### README (excerpt)
**plugged.in 🔌**
**Turn your AI conversations into permanent organizational memory**
[](https://github.com/VeriTeknik/pluggedin-app/releases)
[](https://github.com/VeriTeknik/pluggedin-app/stargazers)
[](LICENSE)
[](https://hub.docker.com/r/veriteknik/pluggedin)
[🚀 Get Started](#-quick-start) • [📚 Documentation](#-documentation) • [🌟 Features](#-key-features) • [💬 Community](#-community--support)
---
🧩 **Now Multi‑Arch Ready!**
Plugged.in Docker images support both `amd64` and `arm64` architectures via a unified manifest.
🧠 **v3.0.0 — Embedded RAG Vector Engine:**
RAG now runs fully in-process using zvec (RocksDB + HNSW). No external services needed — document processing, chunking, and semantic search are all built-in.
---
## 🎯 The Problem We Solve
Every day, you have brilliant conversations with AI - strategy sessions with GPT-4, code reviews with Claude, analysis with Gemini. But when you close that chat window, all that knowledge vanishes. **This is the "AI knowledge evaporation" problem.**
## 💡 The Solution
**plugged.in is the world's first AI Content Management System (AI-CMS)** - a platform that transforms ephemeral AI interactions into persistent, versioned, and searchable organizational knowledge.
Think of it as **"Git for AI-generated content"** meets **"WordPress for AI interactions"**.
---
## ✨ What Makes plugged.in Special
### 🧠 **AI Memory That Persists**
Your AI conversations become permanent assets. Every document is versioned, attributed, and searchable.
### 🤝 **Multi-Model Collaboration**
Claude writes v1, GPT-4 adds technical specs in v2, Gemini refines in v3 - all tracked and attributed.
### 🔌 **Universal MCP Integration**
Works with 1,500+ MCP servers. Connect any tool, any AI, any workflow - all through one interface.
### Source-backed notes
- README provides a Docker Quick Start and opens the app at `http://localhost:12005`.
- README highlights a built-in MCP server hub and integration/discovery features.
- README includes platform stats and describes embedded vector/RAG options for self-hosting.
### FAQ
- **Do I need a separate vector DB?**: Not always—README mentions embedded options; start simple and scale later.
- **Is it only for MCP?**: No—it's an AI knowledge platform, with MCP hub as one core module.
- **What’s the fastest local path?**: Use Docker Compose quick start and confirm you can log in and see the MCP hub UI.
## Source & Thanks
> Created by [VeriTeknik](https://github.com/VeriTeknik). Licensed under MIT.
>
> [VeriTeknik/pluggedin-app](https://github.com/VeriTeknik/pluggedin-app) — ⭐ 94
Thanks to the upstream maintainers and contributors for publishing this work under an open license.
---
## Quick Use
```bash
git clone https://github.com/VeriTeknik/pluggedin-app.git
cd pluggedin-app
cp .env.example .env
docker compose up --build -d
open http://localhost:12005
```
## Intro
PluggedIn 是可自托管的 AI 内容管理系统：内置 RAG 与 MCP Server Hub，把对话沉淀为可版本化知识并统一管理 MCP 集成；已验证 94★，更新于 2026-05-14。
**Best for:** 想要内部知识沉淀平台，并希望用 UI 统一发现/配置 MCP servers 的团队
**Works with:** Docker Compose；Next.js 应用 + Postgres/pgvector；内置 MCP Server Hub（见 README）
**Setup time:** 10-20 minutes
### Key facts (verified)
- GitHub：94 stars · 15 forks；最近更新 2026-05-14。
- 许可证：MIT；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中可对照的入口：`docker compose`。
## Main
- 把它当“AI 内容版 Git”：让对话产出可版本化、可归因，并便于团队协作与审计。
- 用 MCP Hub 统一接入：集中发现、配置与命名空间管理，降低工具冲突与维护成本。
- 先用 Docker Compose 自托管跑通；再评估是否需要外部向量服务（README 也提到内置方案）。
- 安全上把 Token/Key 放到环境变量并定期轮换，把它当内部平台凭据管理。
### README (excerpt)
**plugged.in 🔌**
**Turn your AI conversations into permanent organizational memory**
[](https://github.com/VeriTeknik/pluggedin-app/releases)
[](https://github.com/VeriTeknik/pluggedin-app/stargazers)
[](LICENSE)
[](https://hub.docker.com/r/veriteknik/pluggedin)
[🚀 Get Started](#-quick-start) • [📚 Documentation](#-documentation) • [🌟 Features](#-key-features) • [💬 Community](#-community--support)
---
🧩 **Now Multi‑Arch Ready!**
Plugged.in Docker images support both `amd64` and `arm64` architectures via a unified manifest.
🧠 **v3.0.0 — Embedded RAG Vector Engine:**
RAG now runs fully in-process using zvec (RocksDB + HNSW). No external services needed — document processing, chunking, and semantic search are all built-in.
---
## 🎯 The Problem We Solve
Every day, you have brilliant conversations with AI - strategy sessions with GPT-4, code reviews with Claude, analysis with Gemini. But when you close that chat window, all that knowledge vanishes. **This is the "AI knowledge evaporation" problem.**
## 💡 The Solution
**plugged.in is the world's first AI Content Management System (AI-CMS)** - a platform that transforms ephemeral AI interactions into persistent, versioned, and searchable organizational knowledge.
Think of it as **"Git for AI-generated content"** meets **"WordPress for AI interactions"**.
---
## ✨ What Makes plugged.in Special
### 🧠 **AI Memory That Persists**
Your AI conversations become permanent assets. Every document is versioned, attributed, and searchable.
### 🤝 **Multi-Model Collaboration**
Claude writes v1, GPT-4 adds technical specs in v2, Gemini refines in v3 - all tracked and attributed.
### 🔌 **Universal MCP Integration**
Works with 1,500+ MCP servers. Connect any tool, any AI, any workflow - all through one interface.
### Source-backed notes
- README 提供 Docker Quick Start，并在 `http://localhost:12005` 访问应用。
- README 强调内置 MCP Server Hub，用于集成与发现/配置 servers。
- README 给出平台统计与自托管的向量/RAG 方案描述（含内置能力）。
### FAQ
- **一定要单独的向量数据库吗？**：不一定：README 提到内置方案；先跑通再扩展更稳妥。
- **它只做 MCP 吗？**：不止：它是 AI 知识平台，MCP Hub 是核心模块之一。
- **最快怎么本地跑起来？**：按 Docker Compose Quick Start 跑通，并确认 UI 里能看到 MCP Hub。
## Source & Thanks
> Created by [VeriTeknik](https://github.com/VeriTeknik). Licensed under MIT.
>
> [VeriTeknik/pluggedin-app](https://github.com/VeriTeknik/pluggedin-app) — ⭐ 94
---
Source: https://tokrepo.com/en/workflows/pluggedin-mcp-proxy-server-manager-ui
Author: MCP Hub