広告掲載
MCP.so
ログイン

MCPheonix MCP Server

@jmanhype

リポジトリ

基本情報

カテゴリ

その他

ライセンス

MIT

トランスポート

stdio

作者

jmanhype

MCPheonix MCP Server について

A simplified implementation of the Model Context Protocol (MCP) server using Elixir's Phoenix Framework.

#mcpheonix#model-context-protocol#elixir#phoenix-framework

MCPheonix MCP Server の設定

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": {
    "your_server": {
      "command": "/path/to/executable",
      "args": [
        "arg1"
      ],
      "env": {
        "API_KEY": "value"
      },
      "tools": {
        "tool_name": {
          "description": "What it does",
          "parameters": [
            {
              "name": "param1",
              "type": "string",
              "description": "..."
            }
          ]
        }
      }
    }
  }
}

MCPheonix MCP Server のツール

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。

概要

What is MCPheonix?

MCPheonix is an MCP server built on the Phoenix Framework (Elixir) that exposes Server-Sent Events and JSON-RPC endpoints for MCP clients. It manages multiple child MCP servers as supervised OTP processes, configured via a JSON file. This server is intended for developers who need to orchestrate specialized MCP sub-servers (e.g., Flux image generation, Dart task management) from a single Phoenix web server.

How to use MCPheonix?

Clone the repository, run mix deps.get, then mix phx.server to start the server on port 4001. Child MCP servers are defined in priv/config/mcp_servers.json and are automatically started at boot. Clients connect to GET /mcp/stream for SSE and POST /mcp/rpc for JSON-RPC 2.0 requests.

Key features of MCPheonix

  • Runs a Phoenix web server on port 4001 with SSE and JSON-RPC endpoints.
  • Manages child MCP servers as supervised OTP processes.
  • Supports Flux image generation and Dart task management as built-in child servers.
  • Accepts JSON configuration for adding arbitrary child MCP servers.
  • Event system powered by Broadway and GenStage.
  • Optional Cloudflare Durable Objects integration (experimental).

Use cases of MCPheonix

  • Centralized MCP server routing tool calls to multiple specialized child servers.
  • Managing Flux image generation as a subprocess via MCP.
  • Managing Dart task management as a subprocess via MCP.
  • Building custom MCP server orchestration with Elixir OTP supervision.

よくある質問

1

What runtime dependencies does MCPheonix require?

Elixir >= 1.14, Erlang/OTP >= 25, Phoenix ~> 1.7, Node.js >= 18, and Python >= 3.9 (optional for Flux/Dart).

2

How do I add a new child MCP server?

Edit `priv/config/mcp_servers.json` with the server's command, arguments, environment variables, and tool definitions. The server starts automatically as a supervised process.

3

What MCP endpoints are available?

- `GET /mcp/stream` – SSE stream (returns `x-mcp-client-id` header). - `POST /mcp/rpc` – JSON-RPC 2.0 (requires `x-mcp-client-id` header).

4

Does MCPheonix support authentication?

No. The MCP endpoints currently have no authentication built-in.

5

What are the known limitations?

No authentication, SSE connections are not persisted across restarts, and the Cloudflare Durable Objects integration relies on a custom hex package that may not be publicly available.

コメント

「その他」の他のコンテンツ

Klarix Intelligence Engine

Klarix

B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.

MaxKB

1Panel-dev

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

22.0K

Glasswarp

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

P

PickFu MCP

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

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K
広告掲載