Looking-Glass-MCP: Multi-location Concurrent Network Diagnostic Tool Based on MCP Protocol

Looking Glass MCP

Looking-Glass-MCP is an innovative MCP server that provides network probing capabilities through globally distributed Looking Glass nodes, supporting concurrent execution of network diagnostic operations such as ping, BGP route query, and traceroute at multiple locations.

Developer tools Monitoring #Network probing #Global diagnosis #Multi-node #Asynchronous execution .Python

rating : 2 points

downloads : 6.6K

update time : 2025-07-24

Open Site

What is Looking-Glass-MCP?

Looking-Glass-MCP is a server based on the Model Context Protocol (MCP) that provides probing capabilities for multiple global network nodes. Users can perform network diagnostics on target IPs from different geographical locations, such as ping tests, BGP route queries, and route tracing.

How to use Looking-Glass-MCP?

You can use Looking-Glass-MCP for network probing through simple API calls. You can select specific probing points or let the system automatically select the best probing point, and then send ping, BGP query, or route tracing commands.

Applicable scenarios

It is suitable for scenarios such as CDN performance optimization, network fault troubleshooting, DDoS detection, competitive analysis, and academic research. Whether you are a network engineer or an enterprise decision-maker, you can benefit from it.

Main features

Multi-node probing

Supports simultaneous execution of ping, BGP route query, and route tracing operations from multiple global locations to help comprehensively understand the network status.

Automatic node selection

Automatically selects the best probing node according to the requirements to ensure the accuracy and efficiency of the results.

Multiple probing types

Supports three common network diagnostic methods: ping test, BGP route information query, and route tracing.

Global coverage

Connects to multiple global Looking Glass nodes to provide extensive network probing capabilities.

Asynchronous operation

Implements efficient concurrent operations based on async/await to improve the probing efficiency.

Error handling

Built-in powerful error handling mechanism to ensure the stability and reliability of the probing process.

Advantages

Provides global network probing capabilities to help comprehensively analyze network performance.

Supports multiple probing types to meet different network diagnostic needs.

Automatically selects probing nodes to improve work efficiency.

Asynchronous design improves the probing speed and is suitable for large-scale concurrent tasks.

Limitations

Requires a certain technical foundation to configure and use the API.

Some advanced features may require additional permissions or paid services.

Depends on the availability of external Looking Glass servers.

How to use

Install dependencies

First, install the necessary Python packages, including httpx and mcp[cli].

Get the list of available nodes

Use the list_all_lgs command to view all available probing nodes.

Select a probing node

You can manually specify a probing node or let the system automatically select the optimal node.

Execute a probing command

Use the lg_probing_user_defined or lg_probing_auto_select command to send a probing request.

Usage examples

CDN performance analysis

Analyze the response time of the Google DNS server in different regions to optimize the CDN deployment strategy.

Network fault troubleshooting

Identify network connection problems by tracing the route path and locate the fault point.

BGP route analysis

Check the BGP route information of the target IP to understand its distribution in the global network.

Frequently Asked Questions

Is Looking-Glass-MCP free?

How to select the best probing node?

What commands does Looking-Glass-MCP support?

How to view available probing nodes?

Are the probing results of Looking-Glass-MCP accurate?

Related resources

Official documentation

Detailed usage instructions and API documentation for Looking-Glass-MCP.

GitHub repository

Source code and development information for Looking-Glass-MCP.

Tutorial video

A tutorial video on using Looking-Glass-MCP.

🚀 Looking-Glass-MCP

The first Looking Glass Model Context Protocol (MCP) server, offering network probing capabilities through Looking Glass vantage points!

🚀 Quick Start

Looking-Glass-MCP is a revolutionary MCP server that provides network probing capabilities through Looking Glass (LG) vantage points. This tool allows you to perform network diagnostics and measurements from multiple global locations using a simple, standardized interface.

✨ Features

Multi-VP Probing: Execute network commands from multiple Looking Glass vantage points simultaneously
Auto VP Selection: Automatically select the optimal number of vantage points for your measurements
Comprehensive Commands: Support for ping, BGP route lookups, and traceroute operations
Global Coverage: Access to Looking Glass servers worldwide
Async Operations: Built with async/await for efficient concurrent operations
Error Handling: Robust error handling and timeout management

📦 Installation

pip install -r requirements.txt

💻 Usage Examples

Basic Usage

This example demonstrates how to use Looking-Glass-MCP for CDN performance optimization by analyzing network performance to Google's DNS service (8.8.8.8) from multiple global locations.

Step 1: List Available Vantage Points

# Get all available Looking Glass vantage points
result = await list_all_lgs()

Step 2: Select Global Vantage Points

We selected 5 diverse global locations for comprehensive analysis:

US (Seattle): VP ID 71 - North America
Switzerland: VP ID 164 - Europe
Singapore: VP ID 62 - Asia-Pacific
Australia (Sydney): VP ID 125 - Oceania
Brazil (Campo Grande): VP ID 108 - South America

Step 3: Execute Network Probing

# Run ping tests from 5 global locations
ping_results = await lg_probing_user_defined(
    vp_id_list=["71", "164", "62", "125", "108"],
    cmd="ping",
    target_ip="8.8.8.8"
)

# Run traceroute analysis
traceroute_results = await lg_probing_user_defined(
    vp_id_list=["71", "164", "62", "125", "108"],
    cmd="traceroute", 
    target_ip="8.8.8.8"
)

# Analyze BGP routing information
bgp_results = await lg_probing_user_defined(
    vp_id_list=["71", "164", "62", "125", "108"],
    cmd="bgp",
    target_ip="8.8.8.8"
)

Step 4: LLM-Generated Analysis Results

📊 Example Output: The following analysis was automatically generated by an LLM using the Looking-Glass-MCP tool results. This demonstrates how AI can transform raw network data into actionable business insights.

🤖 LLM Analysis Output (Click to expand)

🌍 Global Network Performance Summary

Location	Country	Latency (avg)	Packet Loss	Performance Rating
Seattle, US	US	~1 - 4ms	0%	⭐⭐⭐⭐⭐ Excellent
Switzerland	CH	~1ms	0%	⭐⭐⭐⭐⭐ Excellent
Singapore	SG	~2.1ms	0%	⭐⭐⭐⭐⭐ Excellent
Sydney, Australia	AU	~0.54ms	0%	⭐⭐⭐⭐⭐ Outstanding
Campo Grande, Brazil	BR	~19.8ms	0%	⭐⭐⭐ Good

🔍 Key Findings

Best Performance:

Australia (Sydney): Exceptionally low latency (~0.54ms) - direct Google peering
Switzerland & US: Sub - millisecond to low single - digit latency

Routing Analysis:

Australia: 6 hops, direct peering with Google infrastructure
Singapore: 4 hops, excellent Google edge presence
Switzerland: 4 hops, optimal European routing
Brazil: 15+ hops, complex ISP routing causing higher latency

BGP Intelligence:

All locations show AS15169 (Google) as origin
Multiple path redundancy visible
Local peering arrangements in major markets

🎯 CDN Optimization Recommendations

Immediate Actions:

Prioritize APAC: Australia and Singapore show excellent performance
European Expansion: Switzerland performance suggests good connectivity
Brazil Improvement: Higher latency indicates need for local presence

Strategic Recommendations:

Multi - CDN Strategy: Deploy edge servers in Sydney, Singapore, and Europe
Peering Optimization: Establish direct peering with major ISPs in Brazil
Performance Monitoring: Use these 5 locations as baseline monitoring points

Expected Impact:

Australia/Singapore: Maintain sub - 2ms response times
Europe: Target sub - 5ms response times
Brazil: Improve from 20ms to <10ms with local presence

💡 Key Insight: This example shows how Looking-Glass-MCP enables AI assistants to automatically analyze complex network data and provide actionable business recommendations - transforming raw technical metrics into strategic insights.

Real - World Applications

This Looking Glass MCP tool is perfect for:

CDN Performance Optimization: Analyze global performance patterns
Network Troubleshooting: Identify routing issues from multiple perspectives
DDoS Detection: Monitor traffic patterns across vantage points
Competitive Analysis: Benchmark against competitor infrastructure
SLA Monitoring: Validate service level agreements globally
Research: Academic studies on internet topology and performance

📚 Documentation

Available Tools

`lg_probing_user_defined`

Send probing commands to a target IP using a specific list of LG vantage points.

Parameters:

vp_id_list: List of Looking Glass VP identifiers
cmd: Command type (ping, show ip bgp, traceroute)
target_ip: Destination IP address for probing

`lg_probing_auto_select`

Send probing commands using automatically selected vantage points.

Parameters:

vp_num: Number of vantage points to use
cmd: Command type (ping, bgp, traceroute)
target_ip: Destination IP address for probing

`list_all_lgs`

Retrieve information about all available Looking Glass vantage points.

🔧 Technical Details

Requirements

Python 3.13+
httpx >= 0.28.1
mcp[cli] >= 1.9.4

🚀 Getting Started

Install dependencies
Configure your MCP client to use Looking-Glass-MCP
Start analyzing global network performance!

The power of Looking Glass combined with MCP's standardized interface makes network analysis accessible and actionable for any application requiring global network intelligence.