vscode-mcp-supergateway

vscode-mcp-supergateway

A centralized MCP gateway that aggregates and routes requests from multiple IDE clients to backend services, while offloading context tasks to local LLM workers.

Category
Visit Server

README

VS Code MCP Supergateway

A centralized, multi-client Model Context Protocol (MCP) gateway that aggregates, routes, and offloads context between IDE clients, local LLM workers, and backend MCP services.


💡 Overview & Value Proposition

As MCP usage grows, managing multiple disjointed MCP servers across different clients (VS Code/Copilot, LM Studio, etc.) becomes cumbersome. VS Code MCP Supergateway acts as a unified hub:

  1. Multiplexing & Routing: Connect multiple clients to a single, orchestrated MCP endpoint.
  2. Context & Token Savings: Keep expensive Frontier Model context clean by delegating repetitive context-structuring tasks to local worker models.
  3. LM Studio Loopback Pattern: Turn LM Studio into both an MCP consumer and a high-speed local MCP tool/worker for tasks like documentation linting, diff summarization, and task management.

🏗 Integration Flow

graph
    subgraph Clients["Clients"]
        Copilot["VS Code / Copilot Chat<br/>(Cloud Frontier Models)"]
        LMStudio_Host["LM Studio Client UI"]
    end

    subgraph Gateway["HTTP MCP Gateway"]
        Supergateway["Supergateway Proxy"]
    end

    subgraph Loopback["Local Worker Loopback"]
        LMStudio_Worker["LM Studio MCP Server<br>(Local Small Models: Gemma, LFM, Qwen, ...)"]
    end

    subgraph Backends["Local MCP Servers"]
        CodebaseMemory["Codebase Memory"]
        MarkdownVault["Markdown Vault<br>(Tasks, ADRs & Specs)"]
        GitLab["GitLab Integration"]
    end

    %% Client connections to Gateway
    Supergateway <-- "Local Memory & Mgmt Tools" --> Clients
    
    %% Gateway routes to Backends and Loopback Worker
    Supergateway --> CodebaseMemory
    Supergateway --> MarkdownVault
    Supergateway --> GitLab
    
    %% Loopback Worker Execution
    Supergateway <-->|"Local Sub-Agents"| LMStudio_Worker
    LMStudio_Worker -. "Reads/Updates" .-> MarkdownVault

⚡ Key Features & Concepts

  • Unified Control Plane: Connect Copilot and LM Studio simultaneously to your underlying toolchain (GitLab, Codebase Memory, Vault).
  • Sub-Agent Loopback: Offload context aggregation, diff generation, and documentation updates to fast local models running in LM Studio without consuming cloud tokens.
  • Markdown Vault Integration: Structure project tasks, architectural decision records (ADRs), and feature specs directly in markdown files guarded by YAML access controls (agent_access).

🚀 Getting Started

Prerequisites

  • Node.js 20+
  • VS Code with GitHub Copilot
  • LM Studio (optional, for local model offloading & loopback)

Installation

git clone https://github.com/Flexi23/vscode-mcp-supergateway.git
cd vscode-mcp-supergateway
npm install
npm run build

🗺 Roadmap & Future Plan

Phase 1: MVP & Core Gateway (Current)

  • [x] Basic stdio / SSE transport routing.
  • [x] Multi-backend server orchestration (Codebase Memory, GitLab, Vault).
  • [x] Initial agent-assisted development groundwork.

Phase 2: LM Studio Loopback & Context Worker

  • [ ] Implement local LM Studio MCP tool wrapper (summarize_diff, generate_adr).
  • [ ] Add zero-blocking async tool handling for local inference.
  • [ ] Graceful fallback & timeout management when local GPUs are under heavy load.

Phase 3: Vault & Task Management Enhancements

  • [ ] Standardized YAML-Frontmatter parser for Markdown Vault (tasks/, adrs/).
  • [ ] Agent scope security layer (agent_access: read | append | edit | hidden).
  • [ ] Automated context bundle generator for Copilot prompts.

📄 License

MIT License. Feel free to contribute or adapt!

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured