Plugged.in

Plugged.in

A unified MCP proxy hub that aggregates multiple MCP servers into one interface.

43
Stars
36
Forks
7
Releases

Overview

The plugged.in MCP Proxy Server is a powerful middleware that aggregates multiple Model Context Protocol (MCP) servers into a single unified interface. It fetches tool, prompt, and resource configurations from the plugged.in App and intelligently routes requests to the appropriate underlying MCP servers. It enables seamless integration with any MCP client (Claude, Cline, Cursor, etc.) while providing management capabilities through the plugged.in ecosystem. Hub pillars include Knowledge (AI document exchange and RAG v2), Memory (persistent, workspace-scoped memory), and Tools (discovery, templates, prompts) with a proxy layer for a single connection per client. The proxy supports STDIO and Streamable HTTP transports, optional API authentication, multi-workspace configurations, and a unified catalog for tools, resources, templates, and prompts. It leverages API-driven capability discovery via the plugged.in App rather than direct discovery, and provides an interactive playground for testing MCP tools and debugging custom MCP servers. It also offers security features, health monitoring, and a play-ready environment for building and testing MCP servers.

Details

Owner
VeriTeknik
Language
TypeScript
License
Apache License 2.0
Updated
2025-12-07

Features

Built-in AI Playground

Test MCPs instantly across models (Claude, Gemini, OpenAI, xAI) without client setup.

Universal MCP Compatibility

Works with any MCP client including Claude Desktop, Cline, and Cursor.

Multi-Server Support

Connect to STDIO, SSE, and Streamable HTTP MCP servers.

Dual Transport Modes

Run the proxy as STDIO (default) or Streamable HTTP server.

Unified Document Search

Search across all connected servers with built-in RAG capabilities.

AI Document Exchange (RAG v2)

MCP servers can create and manage documents in your library with full attribution.

Multi-Workspace Layer

Switch between different sets of MCP configurations with one click.

API-Driven Proxy

Fetches capabilities from plugged.in App APIs rather than direct discovery.

Audience

AI developersBuild, test, and manage multiple MCP servers from a single hub.
MCP integratorsOrchestrate capabilities across diverse MCP servers with unified discovery.
Cloud/DevOps teamsOperate centralized MCP proxy deployments for scalable AI workflows.

Tags

MCPproxyknowledgememorytoolsRAG v2AI document exchangediscoverymulti-serverSTDIOstreamable-httpAPI-driven