Pluggedin
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude,
What is Pluggedin?
Pluggedin is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to crossroads for ai data exchanges. a unified, self-hostable web interface for discovering, configuring, and managing model context protocol (mcp) servers—bringing together ai tools, workspaces, prompts...
The Crossroads for AI Data Exchanges. A unified, self-hostable web interface for discovering, configuring, and managing Model Context Protocol (MCP) servers—bringing together AI tools, workspaces, prompts, and logs from multiple MCP sources (Claude,
This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- The Crossroads for AI Data Exchanges. A unified, self-hostab
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx pluggedin-appConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Pluggedin
plugged.in is a self-hostable AI Content Management System and MCP hub that acts as a unified gateway for discovering, configuring, and managing over 1,500 MCP servers — consolidating tools, workspaces, prompts, and logs from Claude, GPT-4, Gemini, and other AI models into one interface. It transforms ephemeral AI conversations into persistent, versioned, and semantically searchable organizational knowledge using an embedded RAG engine (zvec with RocksDB and HNSW) that requires no external vector database. Developers and teams can self-host the full stack with Docker Compose and use plugged.in as the single MCP endpoint for all their AI clients, with features including OAuth 2.1 authentication, AES-256-GCM encryption, tool prefixing for namespace management, and a live debugging playground.
Prerequisites
- Docker with BuildKit support and at least 8 GB of memory allocated to the Docker engine
- Docker Compose (included with Docker Desktop)
- Git to clone the repository
- An MCP-compatible client such as Claude Desktop, Cursor, or Claude Code CLI
- Optional: a NEXTAUTH_SECRET (generate with openssl rand -base64 32)
Clone the repository and configure environment
Clone the plugged.in app repository and copy the example environment file. At minimum, set NEXTAUTH_SECRET. The bundled PostgreSQL and Redis URLs work out of the box.
git clone https://github.com/VeriTeknik/pluggedin-app.git
cd pluggedin-app
cp .env.example .env
# Edit .env and set: NEXTAUTH_SECRET=$(openssl rand -base64 32)Build and start the full stack
Build the app image from source and start all services including PostgreSQL 18 with pgvector, Redis 7, the database migration, and the Next.js application. The first build takes 10-15 minutes.
docker compose up --build -dMonitor startup
Follow the logs to watch the migration complete and the app become healthy. The web interface will be available at http://localhost:12005 once the app service is running.
docker compose logs -f pluggedin-appOpen the web interface and add MCP servers
Visit http://localhost:12005 and create an account. Use the MCP Server Hub to search for and configure MCP servers from GitHub, npm, or Smithery. plugged.in acts as a proxy, aggregating all configured servers under one endpoint.
Configure your AI client to connect through plugged.in
Point your MCP client at the plugged.in MCP endpoint (HTTP transport). All MCP servers you configure in the web interface will be available through this single connection.
Pluggedin Examples
Client configuration
Claude Desktop configuration pointing to the locally running plugged.in MCP proxy endpoint. Replace YOUR_API_KEY with the API key generated in the plugged.in web interface.
{
"mcpServers": {
"pluggedin": {
"command": "npx",
"args": ["-y", "pluggedin-app"],
"env": {
"PLUGGEDIN_API_KEY": "YOUR_API_KEY",
"PLUGGEDIN_API_BASE_URL": "http://localhost:12005"
}
}
}
}Prompts to try
Sample prompts for interacting with the plugged.in platform and the MCP servers aggregated through it.
- "List all MCP servers currently configured in plugged.in"
- "Search for an MCP server for interacting with GitHub"
- "Save this conversation summary as a document in my plugged.in knowledge base"
- "Search my plugged.in documents for anything related to the Q3 project planning"
- "Show me all AI interactions logged in the last 24 hours"Troubleshooting Pluggedin
docker compose up --build fails with JavaScript heap out of memory
The Next.js build requires significant memory. Increase the memory allocated to Docker in Docker Desktop Settings > Resources to at least 8 GB and retry the build.
The app is unreachable at http://localhost:12005 after the build completes
Check that the migration completed successfully before the app started: docker compose logs pluggedin-migrate. If the migration failed, fix any environment variable issues in .env and run docker compose run --rm pluggedin-migrate to retry.
MCP servers added in the web interface do not appear in the AI client
Ensure your MCP client is configured with the correct API key from the plugged.in web interface and that the PLUGGEDIN_API_BASE_URL points to your running instance. Tool prefixing is applied automatically — server tools will appear with a namespace prefix to avoid conflicts.
Frequently Asked Questions about Pluggedin
What is Pluggedin?
Pluggedin is a Model Context Protocol (MCP) server that crossroads for ai data exchanges. a unified, self-hostable web interface for discovering, configuring, and managing model context protocol (mcp) servers—bringing together ai tools, workspaces, prompts, and logs from multiple mcp sources (claude, It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Pluggedin?
Follow the installation instructions on the Pluggedin GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Pluggedin?
Pluggedin works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Pluggedin free to use?
Yes, Pluggedin is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Pluggedin Alternatives — Similar Developer Tools Servers
Looking for alternatives to Pluggedin? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Pluggedin in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Pluggedin?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.