How is this different from connecting Globalping MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Globalping MCP API changes?

We track the Globalping MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Globalping tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Globalping?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Globalping MCP server myself?

No. TrustGate connects to the Globalping MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Globalping directly.

Connect Globalping MCP to your AI agents, securely.

Q: Is Globalping MCP secure?

The server itself exposes 11 tools, and some of them can write to your Globalping account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Globalping.

One secured endpoint for every Globalping call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Globalping MCP now

What your agents can ask once Globalping MCP is connected.

Select the tools your AI agents can call

11 tools from the Globalping MCP schema.

Showing 11 tools

pingreadPerforms ICMP and packet ping tests to a destination from one or more probe locations.
traceroutereadTraces the network routing hops to a target.
dnsreadResolves DNS queries using specific resolvers and record types.
mtrreadRuns combined ping and traceroute tests, My Traceroute style.
httpreadExecutes HTTP and HTTPS requests from probes worldwide, so the request reaches the target from an address the organization does not control.
locationsreadLists the available Globalping probe regions and filters, which can be continents, country codes, cities, networks and ASNs, or cloud regions.
getMeasurementreadRetrieves the results of a historical measurement by its ID, without running a new test.
compareLocationsreadA helper guide for comparing multi-region performance metrics.
limitsreadDisplays the current free hourly test allowance and any additional credits. The displayed rate limit covers free tests only.
authStatusreadChecks the current MCP authentication status.
helpreadReturns the tool reference and syntax documentation.

What Globalping MCP exposes

Globalping MCP groups its 11 tools into 3 categories, each with a suggested starting policy.

All 11 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Network Tests	ICMP and packet ping to a destination, tracing routing hops to a target, DNS resolution against specific resolvers and record types, combined ping and traceroute with MTR, and HTTP and HTTPS requests issued from probes worldwide	Read	Each call sends real traffic to the target from third-party probes. Restrict the destinations an agent may test to hosts the organization owns, and remember http can reach any URL from an address the organization does not control
Measurements & Locations	Listing the available probe regions and location filters, retrieving the results of a historical measurement by its ID, and a helper guide for comparing performance across several regions	Read	Read-only. getMeasurement retrieves a past result by ID without consuming a new test, which makes it the cheap way to revisit a run
Account & Reference	The current free hourly test allowance and any additional credits, the current authentication status, and the tool reference and syntax documentation	Read	Call limits before a multi-location run: the displayed rate limit covers free tests only, and an authenticated account with credits continues past it at one credit per extra test

Connect Globalping MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Globalping
Find Globalping in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Globalping MCP or block it. You allow the exact tools each agent can call, one by one.

Globalping MCP	11 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 11 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Globalping MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Globalping MCP11 documented tools at mcp.globalping.dev/mcp over streamable HTTP, all read-only. OAuth is the recommended path, with a Bearer API token as the alternative; a legacy /sse endpoint exists for clients without streamable HTTP support.
Coding assistants	Connection & credentialsper user	Network Tests5 tools
Internal copilots	Tool access policiesdeny by default	Measurements & Locations3 tools
Workflow automations	Request & response inspectioninline	Account & Reference3 tools
Compatible MCP clients	Activity monitoringalerts and logs