PluggedIn MCP Proxy Server

Plugged.in MCP Server manages all your other MCPs in one MCP.

typescript

48

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "veriteknik-pluggedin-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@pluggedin/pluggedin-mcp-proxy@latest"
      ],
      "env": {
        "PLUGGEDIN_API_KEY": "YOUR_API_KEY",
        "PLUGGEDIN_API_BASE_URL": "https://plugged.in"
      }
    }
  }
}

You set up the plugged.in MCP Proxy Server to manage and route requests across multiple MCP servers from a single connection. This hub gives you knowledge ground, persistent memory, and tools for downstream models, while centralizing policy, telemetry, and discovery for any MCP client you use.

How to use

Run the proxy in STDIO mode to start quickly and test with an MCP client. You will connect Claude Desktop, Cline, Cursor, or other MCP clients to a single proxy endpoint and access a unified catalog of tools, resources, and prompts.

Start the proxy using a CLI command with your API key. 2) Use an MCP client to connect by configuring a local MCP server reference that points to the proxy. 3) Enable access to downstream MCP servers and begin calling tools, reading resources, and sending prompts through the unified interface.

To connect a client, use a local stdio configuration that launches the proxy via npx and supplies your API key. The following example shows the required shape you would place in your client’s MCP settings.

{
  "mcpServers": {
    "pluggedin": {
      "command": "npx",
      "args": ["-y", "@pluggedin/pluggedin-mcp-proxy@latest"],
      "env": {
        "PLUGGEDIN_API_KEY": "YOUR_API_KEY",
        "PLUGGEDIN_API_BASE_URL": "https://plugged.in"
      }
    }
  }
}

Available tools

pluggedin_discover_tools

Smart discovery with caching to provide instant static and dynamic tool availability across connected MCP servers.

pluggedin_ask_knowledge_base

Query the unified knowledge base with AI filtering and RAG-backed results across documents.

pluggedin_send_notification

Send real-time notifications to users and optionally deliver via email.

pluggedin_create_document

Create new AI-generated documents in your library with attribution and versioning.

pluggedin_list_documents

List and filter documents stored in the library.

pluggedin_search_documents

Search documents with full-text, metadata filters, and snippet generation.

pluggedin_get_document

Retrieve a document by ID with full content and metadata.

pluggedin_update_document

Update or append content to an existing document.

pluggedin_clipboard_set

Store a named clipboard entry or an indexed entry for ordered pipelines.

pluggedin_clipboard_get

Retrieve clipboard entries by name, index, or list all.

pluggedin_clipboard_delete

Delete specific clipboard entries or clear all.

pluggedin_clipboard_list

List all clipboard entries with metadata.

pluggedin_clipboard_push

Push a value onto a stack with auto-incrementing index.

pluggedin_clipboard_pop

Pop the highest-indexed entry from the stack.

pluggedin_rag_query

Perform RAG v2 queries across documents with AI filtering and attribution.