by jsdelivr
Provides LLMs with the ability to execute network measurement commands such as ping, traceroute, DNS, MTR, and HTTP across a global set of probes.
Enables AI models to interact with Globalping’s worldwide network of measurement probes, allowing natural‑language requests like "Ping google.com from 3 locations in Europe" to be turned into real network tests.
https://mcp.globalping.dev/mcp or SSE https://mcp.globalping.dev/sse).npx mcp-remote command.Q: Do I need a Globalping account? A: No, the public API works without authentication, but OAuth provides higher rate limits and access to premium features.
Q: Which LLMs can use this server? A: Any model that implements the Model Context Protocol, including Claude, Anthropic Assistants, Cursor, Windsurf, or custom implementations.
Q: How are credentials supplied?
A: Add your OAuth client ID/secret as Cloudflare Workers secrets (GLOBALPING_CLIENT_ID) and store tokens in the configured KV namespace.
Q: Can I run measurements from a specific cloud provider?
A: Yes, locations support tags like aws-us-east-1, gcp-us-central1, etc., and can be combined using the + syntax.
Q: What transport should I choose? A: The streamable HTTP endpoint is the most widely supported; SSE is useful for environments that prefer event streams.
Globalping is a free, public API that provides access to a globally distributed network of probes for monitoring, debugging, and benchmarking internet infrastructure. With Globalping, you can run network tests (ping, traceroute, DNS, MTR, HTTP) from thousands of locations worldwide.
The Globalping MCP Server implements the Model Context Protocol (MCP), allowing AI models like OpenAI's GPT and Anthropic's Claude to interact with Globalping's network measurement capabilities through natural language.
It also supports oAuth authentication, which offers a secure way to interact with our API and benefits from higher rate limits associated with your account.
The remote MCP server is available under these endpoints:
https://mcp.globalping.dev/mcphttps://mcp.globalping.dev/sseYou can integrate our Globalping MCP server with various AI tools that support the Model Context Protocol.
Here are instructions for the top 3 most popular tools:
Add to your Claude Desktop configuration file (located at %APPDATA%\Claude\config.json on Windows or ~/Library/Application Support/Claude/config.json on macOS):
Streamable HTTP transport:
{
"mcpServers": {
"globalping": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.globalping.dev/mcp"
]
}
}
}
Legacy SSE transport:
{
"mcpServers": {
"globalping": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.globalping.dev/sse"
]
}
}
}
When creating a Claude Assistant in the Anthropic Console:
GlobalpingRun network tests from locations worldwidehttps://mcp.globalping.dev/mcp (Streamable HTTP transport) or https://mcp.globalping.dev/sse (SSE transport)To add the Globalping MCP server to Cursor:
mcp.json config file, where you will need to add:Streamable HTTP transport:
{
"mcpServers": {
"globalping": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.globalping.dev/mcp"
]
}
}
}
Legacy SSE transport:
{
"mcpServers": {
"globalping": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.globalping.dev/sse"
]
}
}
}
This MCP server can be used with any MCP-compatible AI assistant, including:
See the MCP documentation for details on connecting clients to this server.
ping - Perform a ping test to a targettraceroute - Perform a traceroute test to a targetdns - Perform a DNS lookup for a domainmtr - Perform an MTR (My Traceroute) test to a targethttp - Perform an HTTP request to a URLlocations - List all available Globalping probe locationslimits - Show your current rate limits for the Globalping APIgetMeasurement - Retrieve a previously run measurement by IDcompareLocations - Guide on how to run comparison measurementshelp - Show a help message with documentation on available toolsOnce connected to an AI model through a compatible MCP client, you can interact with Globalping using natural language:
Ping google.com from 3 locations in Europe
Run a traceroute to github.com from Japan and compare with traceroute from the US
Check the DNS resolution of example.com using Google DNS (8.8.8.8)
Is jsdelivr.com reachable from China? Test with both ping and HTTP
What's the average response time for cloudflare.com across different continents?
Locations can be specified using the "magic" field, which supports various formats:
You can also combine these with a plus sign for more specific targeting: "London+UK", "Cloudflare+US", etc.
The codebase is organized into modules:
src/index.ts - Main entry point and MCP agent definitionsrc/globalping/types.ts - TypeScript interfaces for the Globalping APIsrc/globalping/api.ts - API wrapper functions for Globalpingsrc/globalping/tools.ts - MCP tool implementationssrc/utils.ts - Helper utilities for rendering the web UIAdd Globalping OAuth credentials:
npx wrangler secret put GLOBALPING_CLIENT_IDUsed for OAuthProvider docs https://github.com/cloudflare/workers-oauth-provider
OAUTH_KVkv_namespaces in the wrangler.jsonc filePlease log in to share your review and rating for this MCP.
{
"mcpServers": {
"globalping": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.globalping.dev/mcp"
],
"env": {}
}
}
}claude mcp add globalping npx mcp-remote https://mcp.globalping.dev/mcpExplore related MCPs that share similar capabilities and solve comparable challenges
by zed-industries
A high‑performance, multiplayer code editor designed for speed and collaboration.
by modelcontextprotocol
Model Context Protocol Servers
by modelcontextprotocol
A Model Context Protocol server for Git repository interaction and automation.
by modelcontextprotocol
A Model Context Protocol server that provides time and timezone conversion capabilities.
by cline
An autonomous coding assistant that can create and edit files, execute terminal commands, and interact with a browser directly from your IDE, operating step‑by‑step with explicit user permission.
by continuedev
Enables faster shipping of code by integrating continuous AI agents across IDEs, terminals, and CI pipelines, offering chat, edit, autocomplete, and customizable agent workflows.
by upstash
Provides up-to-date, version‑specific library documentation and code examples directly inside LLM prompts, eliminating outdated information and hallucinated APIs.
by github
Connects AI tools directly to GitHub, enabling natural‑language interactions for repository browsing, issue and pull‑request management, CI/CD monitoring, code‑security analysis, and team collaboration.
by daytonaio
Provides a secure, elastic infrastructure that creates isolated sandboxes for running AI‑generated code with sub‑90 ms startup, unlimited persistence, and OCI/Docker compatibility.