1. Conduid
  2. Developer Tools
  3. FastMCPTraining
MCP server · Developer Tools

FastMCPTraining

Unclaimed last commit 8 months ago devtools
30Low

Scored 7 months ago · breakdown

About FastMCPTraining

FastMCPTraining is an MCP server published by souri-t in the Developer Tools category.

Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/souri-t/FastMCPTraining

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about FastMCPTraining

Powered by Claude · Grounded in docs

I know everything about FastMCPTraining. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.

5 checks have not been run yet.

README

Dify連携用MCPサーバー(モック)

FastMCPを使用したMCP(Model Context Protocol)サーバーのモック実装です。 Difyや他のAIクライアントから外部システム連携を試すために使用できます。

機能

このMCPサーバーは以下のツールを提供します:

  • get_qa_history: 過去のQA集を取得(モックデータ)
  • get_users: ユーザー名簿を取得(モックデータ)

起動方法

docker compose up -d

接続情報

エンドポイント

http://localhost:8000/sse

MCPサーバーはSSE(Server-Sent Events)トランスポートで起動しています。

Difyからの接続方法

Difyの設定で以下のように指定します:

  1. MCP Server URL: http://localhost:8000/sse
  2. Transport Type: SSE

Pythonクライアントからの接続例

import asyncio
from fastmcp import Client

async def main():
    async with Client("http://localhost:8000/sse") as client:
        # QA履歴を取得
        result = await client.call_tool(
            name="get_qa_history", 
            arguments={}
        )
        print(result)
        
        # ユーザー一覧を取得
        result = await client.call_tool(
            name="get_users", 
            arguments={}
        )
        print(result)

asyncio.run(main())

ログの確認

docker compose logs -f mcp-server

停止方法

docker compose down

ファイル構成

.
├── docker-compose.yml
├── mcp_server/
│   ├── main.py           # MCPサーバー本体
│   ├── requirements.txt  # Python依存パッケージ
│   └── Dockerfile        # Dockerイメージ定義
└── README.md

カスタマイズ

mcp_server/main.pyを編集して、新しいツールを追加したり、既存のモックデータを変更できます。

@mcp.tool()
def your_custom_tool(param: str) -> dict:
    """あなたのカスタムツール"""
    return {"result": "カスタム結果"}

変更後は再ビルドが必要です:

docker compose down
docker compose build
docker compose up -d

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About FastMCPTraining

How do I install FastMCPTraining?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is FastMCPTraining safe to use with an AI agent?

Its trust score is 30 out of 100 (low). It passes 1 of the 1 static security checks run so far. It has no ConduID identity yet, so agent calls to it are not receipted.

Is FastMCPTraining still maintained?

The last commit was 8 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.