general MCP Server
Plugged.in MCP Server manages all your other MCPs in one MCP.
Discovered via unknown and last synced 1w ago.
1. Install the package
npx -y @pluggedin/pluggedin-mcp-proxy@latest
2. Add to claude_desktop_config.json
{
"mcpServers": {
"pluggedin-pluggedin-mcp-proxy": {
"command": "npx",
"args": [
"-y",
"@pluggedin/pluggedin-mcp-proxy@latest"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
AI engineers and prompt developers who manage multiple MCP servers and want centralized control. DevOps teams and AI infrastructure maintainers benefit from simplified MCP orchestration without juggling separate server configurations.
Instead of configuring and maintaining separate MCP connections, route all your MCP servers through a single proxy endpoint. This simplifies your Claude integration architecture and reduces configuration complexity.
Manage authentication, rate limiting, and request logging for all connected MCPs in one place. Monitor usage patterns across your entire MCP ecosystem without instrumenting individual servers.
Dynamically discover and switch between different MCP server configurations at runtime. Enable capability-based routing where Claude selects the appropriate MCP backend based on task requirements.
Maintain a single proxy layer that routes to different MCP servers across dev, staging, and production environments. Reduce deployment complexity by managing environment-specific MCP selection at the proxy level.
The proxy intercepts Claude's MCP protocol requests and forwards them to the configured backend servers, aggregating responses back to Claude. It acts as a transparent intermediary that normalizes communication between Claude and your MCP ecosystem.
Behavior depends on your proxy configuration. Most implementations support fallback servers, circuit breakers, or graceful degradation to notify Claude when a specific capability is unavailable.
Yes, you can deploy multiple proxy instances behind a load balancer. Each instance manages its own MCP connections, so horizontal scaling is supported for high-availability setups.
Latency overhead is minimal since the proxy primarily routes and buffers messages. Actual response time depends on your underlying MCP servers. Most deployments see negligible additional latency (< 50ms).
API key from plugged.in App
Description
Base URL for plugged.in App
Description