What session modes are available?
The server supports two modes controlled by `SHARED_SESSION`: shared mode (default, all clients share one MCP session) and independent mode (each client creates a separate MCP session).
@jinyalong
基本情報
Start any MCP Server remotely using the MCP standard protocol.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcpproxy": {
"command": "python",
"args": [
"main.py"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
The MCP SSE Proxy Server is a Server-Sent Events (SSE) based Model Context Protocol (MCP) proxy server that enables remote execution of MCP servers using the standard MCP protocol. It supports both shared and independent session modes.
Configure via environment variables (AUTH_KEY, SHARED_SESSION, MCP_SERVER_CONFIG) and run the server using Python (python main.py) or Docker (docker run codefriday123/mcpproxy:1.0). Connect clients to the GET /sse endpoint and send JSON-RPC messages to the returned message endpoint via POST /messages.
The server supports two modes controlled by `SHARED_SESSION`: shared mode (default, all clients share one MCP session) and independent mode (each client creates a separate MCP session).
Set the `AUTH_KEY` environment variable; all requests must then provide this key as a URL parameter `auth_key`.
In independent session mode, pass custom environment variables as URL query parameters on the SSE connection (e.g., `GET /sse?auth_key=xxx&GITHUB_PERSONAL_ACCESS_TOKEN=ghp_xxxx`).
Pull the image `codefriday123/mcpproxy:1.0` and run with `-p 8000:8000`, setting `AUTH_KEY`, `SHARED_SESSION`, and `MCP_SERVER_CONFIG` environment variables.
Add an entry to Cursor's `mcp.json` configuration with the server’s SSE URL and the `auth_key` parameter.
Open-source MCP to use Blender with any LLM

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w
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

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
コメント