Back to MCP directory
publicPublicdnsLocal runtime

cleanuri-url-shortener-mcp

提供了一个使用 CleanURI API 缩短 URL 的简单工具,该工具设计为 FastMCP 服务器运行,可以与基于代理或工具的系统集成。

article

README

MseeP.ai Security Assessment Badge

URL Shortener MCP Tool

smithery badge

URL Shortener MCP server

This project provides a simple URL shortening tool using the CleanURI API and is designed to run as a FastMCP server tool.

✨ Features

  • Shortens any given URL using the CleanURI API.
  • Exposes the functionality as a tool via FastMCP.
  • Includes proper error handling and response validation.
  • Designed to run via stdio transport for integration with agent or tool-based systems.

🚀 Usage

1. Requirements

  • Python 3.10+
  • httpx
  • fastmcp

2. Installation

Installing via Smithery

To install URL Shortener Tool for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @Talismanic/cleanuri-url-shortener-mcp --client claude

Manual Installation

uv add httpx 'mcp[cli]'

Docker Installation:

docker build -t url-shortener .

3. Running

uv run main.py

For docker based use, we dont need to do anything here.

4. Adding in Claude Desktop

With the uv

{
  "mcpServers": {
    "url-shortener": {
      "command": "/Users/{userName}/.local/bin/uv",
      "args": [
        "--directory",
        "{path_to_repo}/cleanuri-url-shortener-mcp",
        "run",
        "main.py"
      ]
    }
  }
}

With Docker

{
  "mcpServers": {
    "url-shortener": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--init",
        "-e",
        "DOCKER_CONTAINER=true",
        "url-shortener"
      ]
    }
  }
}
help

Runtime guide

cloud

Hosted runtime

Hosted servers run from a provider-managed environment. You usually connect the MCP client to the hosted endpoint or follow the provider's authorization flow, without keeping a local process alive

  1. Open provider connection page
  2. Authorize or copy endpoint
  3. Connect from your MCP client
terminal

Local runtime / other methods

Local servers run on your own machine or infrastructure. You normally copy the server_config into your MCP client, install the required package, and provide env variables from env_schema when needed

  1. Copy server_config
  2. Install required package
  3. Fill env variables and restart client