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.
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:
- Multiplexing & Routing: Connect multiple clients to a single, orchestrated MCP endpoint.
- Context & Token Savings: Keep expensive Frontier Model context clean by delegating repetitive context-structuring tasks to local worker models.
- 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
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!
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。