Skip to main content
Glama

mcp-internet-speed-test

MIT License
7
  • Apple
  • Linux

MCP Internet Speed Test

⚠️ Experimental Version

This is an experimental implementation of a Model Context Protocol (MCP) server for internet speed testing. It allows AI models and agents to measure, analyze, and report network performance metrics through a standardized interface.

What is MCP?

The Model Context Protocol (MCP) provides a standardized way for Large Language Models (LLMs) to interact with external tools and data sources. Think of it as the "USB-C for AI applications" - a common interface that allows AI systems to access real-world capabilities and information.

Features

  • Download Speed Testing: Measure download bandwidth
  • Upload Speed Testing: Measure upload bandwidth with configurable file sizes
  • Latency Testing: Measure network latency to various servers
  • Jitter Analysis: Calculate network jitter by analyzing latency variations
  • Comprehensive Reporting: Provide detailed JSON-formatted reports

Installation

Prerequisites

  • Python 3.12 or higher
  • uv package manager (recommended)

The uvx command is a convenient way to run Python packages directly without explicit installation:

# Run the MCP server directly uvx /path/to/mcp-internet-speed-test

Option 2: Using docker

# Build the Docker image docker build -t mcp-internet-speed-test . # Run the MCP server in a Docker container docker run -it --rm -v $(pwd):/app -w /app mcp-internet-speed-test

Configuration

To use this MCP server with Claude Desktop or other MCP clients, add it to your MCP configuration file.

Claude Desktop Configuration

Edit your Claude Desktop MCP configuration file:

{ "mcpServers": { "mcp-internet-speed-test": { "command": "uv", "args": [ "--directory", "/ABSOLUTE/PATH/TO/mcp-internet-speed-test", "run", "main.py" ] } } }

API Tools

The MCP Internet Speed Test provides the following tools:

  1. measure_download_speed: Measures download bandwidth (in Mbps)
  2. measure_upload_speed: Measures upload bandwidth (in Mbps)
  3. measure_latency: Measures network latency (in ms)
  4. measure_jitter: Measures network jitter by analyzing latency variations
  5. run_complete_test: Runs all tests and provides a comprehensive report

Troubleshooting

If you're having issues connecting to the MCP server:

  1. Make sure the path in your MCP configuration is correct
  2. Check that you have the required permissions for the directory
  3. Verify Python 3.12+ is installed and in your PATH
  4. Ensure the mcp[cli] and httpx packages are installed

Development

This is an experimental project and contributions are welcome. To contribute:

  1. Open an issue or submit a pull request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

  • MCP Framework maintainers for standardizing AI tool interactions
  • The Model Context Protocol community for documentation and examples
Install Server
A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

mcp-internet-speed-test

  1. ⚠️ Experimental Version
    1. What is MCP?
      1. Features
        1. Installation
          1. Prerequisites
          2. Option 1: Using uvx (Recommended)
          3. Option 2: Using docker
        2. Configuration
          1. Claude Desktop Configuration
        3. API Tools
          1. Troubleshooting
            1. Development
              1. License
                1. Acknowledgments

                  Related MCP Servers

                  View all related MCP servers

                  MCP directory API

                  We provide all the information about MCP servers via our MCP API.

                  curl -X GET 'https://glama.ai/api/mcp/v1/servers/inventer-dev/mcp-internet-speed-test'

                  If you have feedback or need assistance with the MCP directory API, please join our Discord server