MCP.so
ログイン

Fledge MCP Server

@Krupalp525

リポジトリ

Fledge MCP Server について

Fledge Model Context Protocol (MCP) Server for Cursor AI integration

#fledge#mcp#cursor-ai

基本情報

カテゴリ

その他

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

Krupalp525

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": {
    "fledge-mcp": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "fledge-mcp",
        "."
      ]
    }
  }
}

ツール

ツールは検出されませんでした

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 Fledge MCP Server?

A Model Context Protocol (MCP) server that connects Fledge functionality to Cursor AI, allowing the AI to interact with Fledge instances via natural language commands. It requires Fledge installed locally or accessible via API (default: http://localhost:8081).

How to use Fledge MCP Server?

Install dependencies with pip install -r requirements.txt, ensure Fledge is running (fledge start), then launch the server with python mcp_server.py or python secure_mcp_server.py for API‑key authentication. In Cursor AI, add an MCP server with URL http://localhost:8082/tools and optionally the X-API-Key header. Test by typing “Check if Fledge API is reachable” in Cursor’s Composer.

Key features of Fledge MCP Server

  • Exposes 16 tools for data access, service control, and UI generation
  • Supports secure API key authentication via secure_mcp_server.py
  • Implements JSON-RPC 2.0 over WebSocket transport
  • Generates React components for Fledge data visualization
  • Enables real-time sensor data subscriptions and latest readings
  • Can be deployed on Smithery.ai for enhanced scalability

Use cases of Fledge MCP Server

  • Validate Fledge API connectivity using natural language commands
  • Fetch and filter sensor data for analysis or visualization
  • Generate mock sensor data for testing and development
  • Start or stop Fledge services via Cursor AI commands
  • Create frontend UI components for Fledge dashboards

FAQ from Fledge MCP Server

What are the prerequisites?

Fledge installed locally or accessible via API, Cursor AI, and Python 3.8+.

How does secure mode work?

Run python secure_mcp_server.py. It generates an API key stored in api_key.txt. All requests must include the X-API-Key header; the health endpoint remains unauthenticated.

What transport does the server use?

The server uses WebSocket transport and the Model Context Protocol implemented via JSON-RPC 2.0.

Can it be deployed to the cloud?

Yes, it can be deployed on Smithery.ai using Docker and the smithery CLI, with configurable environment variables for the Fledge API URL and API key.

How to add new tools?

Add the tool definition to tools.json and implement the handler in both mcp_server.py and secure_mcp_server.py.

コメント

「その他」の他のコンテンツ

MCP Go 🚀

mark3labs

A Go implementation of the Model Context Protocol (MCP), enabling seamless integration between LLM applications and external data sources and tools.

8.9K

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

Inbox Zero AI MCP

elie222

The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.

11.6K

Peekaboo MCP – lightning-fast macOS screenshots for AI agents

steipete

Peekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.

4.8K

MCP Toolbox for Databases

googleapis

MCP Toolbox for Databases is an open source MCP server for databases.

15.9K