mcp-gateway
Aggregates multiple child MCP servers into a single MCP server endpoint, enabling clients to use various tools (e.g., filesystem, Brave Search) through one interface.
README
mcp-gateway
複数の子 MCP サーバーを束ねて、単一の MCP サーバーとして公開するゲートウェイ。
起動
llama-server -m model.gguf --ui-mcp-proxy
仕組み
llama-server(または任意の MCP クライアント)が POST /mcp に接続し、ツール一覧取得・実行を行う。ゲートウェイは子 MCP サーバー群にリクエストをルーティングし、結果を返す。
MCPクライアント(llama-server など)
↓ MCP over HTTP (POST /mcp)
mcp-gateway :8787
↙ ↓ ↘
filesystem brave ...子MCPサーバー群
セットアップ
cp .env.example .env # 必要に応じて PORT を変更
mkdir -p data # filesystem-mcp の対象ディレクトリ
docker compose up --build
子 MCP サーバーの追加
servers.json(プロジェクトルート。data/ の中ではない)にブロックを追加するだけ:
{
"filesystem": { "command": "npx", "args": ["-y", "@modelcontextprotocol/server-filesystem", "/data"] },
"brave": { "command": "npx", "args": ["-y", "@modelcontextprotocol/server-brave-search"], "env": { "BRAVE_API_KEY": "..." } }
}
MCP エンドポイント
| メソッド | パス | 説明 |
|---|---|---|
| POST | /mcp |
MCP JSON-RPC(リクエスト・通知) |
動作確認
# initialize
curl http://localhost:8787/mcp \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"0"}}}'
# tools/list
curl http://localhost:8787/mcp \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/list"}'
# tools/call(ツール名は <サーバー名>__<ツール名> の形式)
curl http://localhost:8787/mcp \
-H 'content-type: application/json' \
-d '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"filesystem__read_file","arguments":{"path":"/data/hello.txt"}}}'
開発
pnpm install
pnpm test # vitest
pnpm lint # biome
pnpm dev # tsx で起動
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.