What are the technical prerequisites?
Node.js 18+ (recommended v20+). An API key from plugged.in App is required to fetch configurations and use the hub features.
@VeriTeknik
基本信息
Plugged.in MCP Server manages all your other MCPs in one MCP.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"pluggedin-mcp-proxy": {
"command": "npx",
"args": [
"-y",
"@pluggedin/pluggedin-mcp-proxy@latest",
"--pluggedin-api-key",
"YOUR_API_KEY"
]
}
}
}Get started with Plugged.in MCP - shows setup instructions and API key configuration (no API key required)
Triggers discovery of tools (and resources/templates) for configured MCP servers in the Pluggedin App.
Ask questions and get AI-generated answers from your knowledge base. Returns structured JSON with answer, document sources, and metadata.
Create and save AI-generated documents to the user's library in Plugged.in (requires API key)
List documents with filtering options from the user's library (requires API key)
Search for specific documents in your library. Returns document metadata (ID, title, snippet). To retrieve full content, use pluggedin_get_document with the returned document ID.
Retrieve a specific document's full content by ID. Use this after pluggedin_search_documents to get the complete content of documents you found. Set includeContent=true to get the full text.
Update or append to an existing AI-generated document (requires API key)
Send custom notifications through the Plugged.in system with optional email delivery. You can provide a custom title or let the system use a localized default.
List notifications from the Plugged.in system with optional filters for unread only and result limit
Mark a notification as done in the Plugged.in system
Delete a notification from the Plugged.in system
Set a clipboard entry by name (semantic key) or index (array-like). Named entries are upserted; indexed entries fail if index exists. Max 2MB per entry.
Get clipboard entries. Specify name or idx for a single entry, or omit both to list all entries with pagination.
Delete clipboard entries by name, index, or clear all entries.
List all clipboard entries with metadata. Image values are truncated to first 1000 chars for preview.
Push a value to the indexed clipboard with auto-incrementing index. Useful for building ordered pipelines or stack-like operations.
Pop the highest-indexed entry from the clipboard (LIFO behavior). Returns the entry value and removes it.
Start a new memory session to begin capturing observations. Returns a session UUID and memory_session_id for subsequent operations.
End a memory session and trigger Z-report generation (AI-compressed session summary).
Record an observation during a memory session. Observations are classified by the Analytics Agent into memory ring types (procedures, practice, longterm, shocks).
Search memories using semantic similarity. Returns lightweight results (50-150 tokens each) for token-efficient progressive disclosure. Use pluggedin_memory_details for full content.
Get full details for selected memories (progressive disclosure Layer 3). Use after pluggedin_memory_search to retrieve complete content for specific memories.
A 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, providing built-in Knowledge (RAG v2), persistent Memory (clipboard system), Tools, and Proxy capabilities for any MCP client.
Requires Node.js 18+ and an API key from plugged.in (get at plugged.in/api-keys). Install and run via npx -y @veriteknik/pluggedin-mcp. The proxy runs in STDIO mode by default or can be started as a Streamable HTTP server with optional Bearer token authentication. Configuration is managed through the plugged.in App, not local config files.
Node.js 18+ (recommended v20+). An API key from plugged.in App is required to fetch configurations and use the hub features.
The proxy aggregates multiple MCP servers into one unified connection, adding built‑in tools (discovery, RAG, notifications, clipboard memory) and central management through the plugged.in App.
Downstream: STDIO, SSE, and Streamable HTTP. Upstream: the proxy itself can run as STDIO (default) or Streamable HTTP server with optional API authentication and stateless mode.
Yes. Clipboard entries are scoped to profiles/workspaces in the plugged.in App and survive session boundaries. Entries can be set by name or index, pushed/popped as a stack, and listed with metadata.
Yes. It works with any MCP client, including Claude Desktop, Cline, Cursor, and MCP Inspector, by pointing the client’s MCP configuration to the proxy’s STDIO or Streamable HTTP endpoint.
不止于 CSS

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

The article (der, die, das) of 90,000 German nouns, compounds included, plus a checker that finds wrong articles in German text (“mit der Zug” → dem). Uses dictionary data, not AI guessing. Free, no login.
🚀 The fast, Pythonic way to build MCP servers and clients.
评论