How is this different from connecting Google Cloud Compute Engine 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 Google Cloud Compute Engine MCP API changes?

We track the Google Cloud Compute Engine 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 Google Compute Engine 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 Google Compute Engine?

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 Google Cloud Compute Engine MCP server myself?

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

Connect Google Cloud Compute Engine MCP to your AI agents, securely.

Q: Is Google Cloud Compute Engine MCP secure?

The server itself exposes 29 tools, and some of them can write to your Google Compute Engine 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 Google Compute Engine.

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

Get started for free

Get a demo

Try Google Cloud Compute Engine MCP now

What your agents can ask once Google Cloud Compute Engine MCP is connected.

Select the tools your AI agents can call

29 tools from the Google Cloud Compute Engine MCP schema.

Showing 29 tools

list_instancesreadRetrieves the list of VM instances contained within the specified zone.
start_instancewriteStarts an instance that was stopped using the stop method.
stop_instancewriteStops a running instance, shutting it down cleanly.
reset_instancehigh riskPerforms a hard reset on the instance. This is equivalent to cycling the power, and data may be lost.
delete_instancehigh riskDeletes the specified VM instance resource.
create_instancewriteCreate a new Google Compute Engine virtual machine (VM) instance.
get_instance_basic_inforeadGet basic information about a Compute Engine VM instance, including its name, ID, status, machine type, creation timestamp, and attached guest accelerators.
set_instance_machine_typewriteSets the machine type for a stopped Google Compute Engine instance to the specified machine type.
get_instance_group_manager_basic_inforeadGet basic information about a Compute Engine managed instance group (MIG), including its name, ID, instance template, base instance name, target size, target stopped size, target suspended size, status and creation timestamp.
list_instance_group_managersreadLists Compute Engine managed instance groups (MIGs).
list_managed_instancesreadLists managed instances for a given managed instance group (MIG).
list_instance_templatesreadLists Compute Engine instance templates. Details for each instance template include name, ID, description, machine type, region, and creation timestamp. Requires project as input.
get_instance_template_basic_inforeadGet basic information about a Compute Engine instance template, including its name, ID, description, machine type, region, and creation timestamp. Requires project and instance template name as input.
get_instance_template_propertiesreadGet instance properties of a Compute Engine instance template.
list_disksreadRetrieves a list of persistent disks contained within the specified zone.
list_snapshotsreadRetrieves the list of snapshots contained within the specified project.
list_instance_attached_disksreadLists the disks attached to a Compute Engine virtual machine (VM) instance.
get_disk_basic_inforeadGet basic information about a Compute Engine disk, including its name, ID, description, creation timestamp, size, type, status, last attach timestamp, and last detach timestamp.
get_disk_performance_configreadGet performance configuration of a Compute Engine disk, including its type, size, provisioned IOPS, provisioned throughput, physical block size, storage pool and access mode.
list_imagesreadRetrieves the list of custom images available to the specified project.
list_machine_typesreadRetrieves a list of machine types available to the specified project in the given zone.
list_accelerator_typesreadLists the available Google Compute Engine accelerator types.
get_zone_operationreadRetrieves the specified zone-specific operation resource.
get_reservation_basic_inforeadGet Compute Engine reservation basic info including name, ID, creation timestamp, zone, status, specific reservation required, commitment, and linked commitments.
get_reservation_detailsreadGet Compute Engine reservation details. Returns reservation details including name, ID, status, creation timestamp, specific reservation properties like machine type, guest accelerators and local SSDs, aggregate reservation properties like VM family and reserved resources, commitment and linked commitments, sharing settings, and resource status. Requires project, zone, and reservation name as input.
list_reservationsreadLists Compute Engine reservations. Details for each reservation include name, ID, creation timestamp, zone, status, specific reservation required, commitment, and linked commitments. Requires project and zone as input.
list_commitmentsreadLists Compute Engine Commitments in a region. Details for each commitment include name, ID, status, plan, type, resources, and creation, start and end timestamps. Requires project and region as input.
get_commitment_basic_inforeadGet basic information about a Compute Engine Commitment, including its name, ID, status, plan, type, resources, and creation, start and end timestamps.
list_commitment_reservationsreadLists reservations for a Compute Engine Commitment.

What Google Cloud Compute Engine MCP exposes

Google Cloud Compute Engine MCP groups its 29 tools into 4 categories, each with a suggested starting policy.

All 29 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Instances	VM listing, details, creation, start, stop, reset, deletion, machine type changes, instance groups and templates	Read / Write	Approve creation and deletion; audit power state changes
Disks & Snapshots	Persistent disks, snapshots, attachment and resizing	Read / Write	Require approval for disk deletion
Images & Machine Types	Images, image families and available machine types	Read	Allow catalog lookups
Operations	Zone, region and global operation status	Read	Allow status checks

Connect Google Cloud Compute Engine 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 Google Compute Engine
Find Google Compute Engine 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 Google Cloud Compute Engine MCP or block it. You allow the exact tools each agent can call, one by one.

Google Cloud Compute Engine MCP	29 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 29 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 Google Cloud Compute Engine 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.	Google Cloud Compute Engine MCP29 documented tools.
Coding assistants	Connection & credentialsper user	Instances14 tools
Internal copilots	Tool access policiesdeny by default	Operations7 tools
Workflow automations	Request & response inspectioninline	Disks & Snapshots5 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools3 tools