Connectors · Observability & analytics

Google Cloud Monitoring MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Google Cloud Monitoring and the rest of your systems. It gives your agent 73 Google Cloud Monitoring actions (40 reads, 24 writes and 9 that wait for a confirmation) and holds the Google Cloud Monitoring credential itself, so the agent never does. It paces Google Cloud Monitoring's limits and records every call. Connecting Google Cloud Monitoring needs your own Google Cloud Monitoring OAuth app and one admin sign-in.

Connect Google Cloud Monitoring free See pricing

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp

73actionsin one signed file
40readlook, never change
24writecreate and update
9wait for a yesdestructive, confirmed first

Set up

Connect Google Cloud Monitoring in three steps.

01
Add actionlake to Claude.
Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.
https://connect.actionlake.com/mcp
02
Connect Google Cloud Monitoring.
OAuth 2.0, authorization code with PKCE. You register your own OAuth app with Google Cloud Monitoring, an admin signs in once, and you paste the app's client id and secret and the tokens from that sign-in; actionlake renews the access token from then on. actionlake stores what you paste write-only, sealed under your tenant's key.
Before the first sign-in, Google Cloud Monitoring needs an OAuth app of your own, registered in its developer portal. actionlake has no Google Cloud Monitoring app to lend you.
- access_tokenAccess token from one sign-in with your own OAuth app
- refresh_tokenRefresh token from the same sign-in; the access token is renewed from it
- client_idGoogle OAuth client id (Google Cloud console > APIs & Services > Credentials; enable the Cloud Monitoring API on the…
- client_secretGoogle OAuth client secret
```
account { op: "connections.requirements", service: "gcp_cloud_monitoring" }
# free: exactly what to paste, and what is found for you
```

Make the first call. Check before a write.

Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

do    { action: "gcp_cloud_monitoring.uptime_check_ips.list" }# uptime check ips: list · read · 1 upstream callcheck { action: "gcp_cloud_monitoring.alert_policies.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Google Cloud Monitoring at a glance

Sign-in: OAuth 2.0, authorization code with PKCE. You register your own OAuth app with Google Cloud Monitoring, an admin signs in once, and you paste the app's client id and secret and the tokens from that sign-in; actionlake renews the access token from then on.
You provide: access_tokenrefresh_tokenclient_idclient_secret
Limits we pace to: 600 calls a minute, per connection
API covered: Google Cloud Monitoring (metrics, time series, alert policies, alerts, uptime checks, notification channels, SLOs, dashboards, PromQL) API monitoring v3 (Discovery revision 20261015) + monitoring v1 (Discovery revision 20261015)monitoring.googleapis.com
Built from: Google Cloud Monitoring's documentation, read 23 October 2026monitoring.googleapis.com monitoring.googleapis.com cloud.google.com
Service file: Version 1.0.0, signed (Ed25519)
Cached reads: 33 of 40 reads, for up to 5 minutes; a write clears what it affects
Shared entities: 3, so ask can line Google Cloud Monitoring up with your other systems
Data: Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in Google Cloud Monitoring.

73 actions in 24 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

40readlook, never change
24writecreate and update
9destructivewait for a confirmation

Notification channels
8
2 read · 5 write · 1 destructive
Projects notification channels: list · Projects notification channels: create · Projects notification channels: get · Projects notification channels: patch
Alert policies
5
2 read · 2 write · 1 destructive
Projects alert policies: list · Projects alert policies: create · Projects alert policies: get · Projects alert policies: patch
Dashboards
5
2 read · 2 write · 1 destructive
Projects dashboards: list · Projects dashboards: create · Projects dashboards: get · Projects dashboards: patch
Groups
5
2 read · 2 write · 1 destructive
Projects groups: create · Projects groups: list · Projects groups: get · Projects groups: update
Prometheus
5
5 read · 0 write · 0 destructive
Projects location prometheus api v1: labels · Projects location prometheus api v1: query · Projects location prometheus api v1: query exemplars · Projects location prometheus api v1: query range
Service level objectives
5
2 read · 2 write · 1 destructive
Services service level objectives: create · Services service level objectives: list · Services service level objectives: get · Services service level objectives: patch
Services
5
2 read · 2 write · 1 destructive
Services: list · Services: create · Services: get · Services: patch
Uptime check configs
5
2 read · 2 write · 1 destructive
Projects uptime check configs: create · Projects uptime check configs: list · Projects uptime check configs: get · Projects uptime check configs: patch

16 more areas · 30 actions

Metric descriptors 4
Snoozes 4
Time series 4
Alerts 2
Metrics scope projects 2
Metrics scopes 2
Monitored resource descriptors 2
Notification channel descriptors 2
Collectd time series 1
Folders time series 1
Group members 1
Operations 1
Organizations time series 1
Prometheus label 1
Prometheus metadata 1
Uptime check ips 1

Top actions

The Google Cloud Monitoring API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 43 of Google Cloud Monitoring's 43 action names are shared with at least one other connector, so an agent learns them once.

Action	What it does	Effect	Same name in
`gcp_cloud_monitoring.alerts.list`Projects alerts: list	Lists the existing alerts for the metrics scope of the project.	read	`monitoring.alert.list`51 connectors
`gcp_cloud_monitoring.alert_policies.list`Projects alert policies: list	Lists the existing alerting policies for the workspace.	read	`monitoring.monitor.list`32 connectors
`gcp_cloud_monitoring.services.list`Services: list	List Services for this Metrics Scope.	read	`monitoring.service.list`12 connectors
`gcp_cloud_monitoring.alert_policies.create`Projects alert policies: create	Creates a new alerting policy.Design your application to single-thread API calls that modify the state of alerting policies in a single project.	write	`monitoring.monitor.create`27 connectors
`gcp_cloud_monitoring.services.create`Services: create	Create a Service.	write	`monitoring.service.create`11 connectors
`gcp_cloud_monitoring.alerts.get`Projects alerts: get	Gets a single alert.	read	`monitoring.alert.get`33 connectors
`gcp_cloud_monitoring.alert_policies.delete`Projects alert policies: delete	Deletes an alerting policy.Design your application to single-thread API calls that modify the state of alerting policies in a single project.	destructive	`monitoring.monitor.delete`31 connectors
`gcp_cloud_monitoring.notification_channels.list`Projects notification channels: list	Lists the notification channels that have been created for the project.	read	`monitoring.notification_channel.list`18 connectors
`gcp_cloud_monitoring.notification_channels.create`Projects notification channels: create	Creates a new notification channel, representing a single notification endpoint such as an email address, SMS number, or PagerDuty service.Design your…	write	`monitoring.notification_channel.create`16 connectors
`gcp_cloud_monitoring.dashboards.list`Projects dashboards: list	Lists the existing dashboards.This method requires the monitoring.dashboards.list permission on the specified project.	read	`monitoring.dashboard.list`15 connectors
`gcp_cloud_monitoring.dashboards.create`Projects dashboards: create	Creates a new custom dashboard.	write	`monitoring.dashboard.create`13 connectors
`gcp_cloud_monitoring.time_series.list`Projects time series: list	Lists time series that match a filter.	read	`monitoring.metric.list`10 connectors

Try it

Prompts to paste into Claude.

Each one names the Google Cloud Monitoring actions it will call, so you know what it reads and what it changes before you send it.

Readread
Which Google Cloud Monitoring alerts are open right now? Group them by service.
callsgcp_cloud_monitoring.alerts.list
Writewrite
Projects alert policies: create in Google Cloud Monitoring. Show me exactly what you will send before you save it.
callsgcp_cloud_monitoring.alert_policies.create

Governance for Google Cloud Monitoring

Destructive actions wait for a yes.

9 Google Cloud Monitoring actions are destructive. These are all of them:

Projects alert policies: deletegcp_cloud_monitoring.alert_policies.delete
Services: deletegcp_cloud_monitoring.services.delete
Projects notification channels: deletegcp_cloud_monitoring.notification_channels.delete
Projects dashboards: deletegcp_cloud_monitoring.dashboards.delete
Services service level objectives: deletegcp_cloud_monitoring.service_level_objectives.delete
Projects uptime check configs: deletegcp_cloud_monitoring.uptime_check_configs.delete
Projects metric descriptors: deletegcp_cloud_monitoring.metric_descriptors.delete
Projects groups: deletegcp_cloud_monitoring.groups.delete
Locations global metrics scopes projects: deletegcp_cloud_monitoring.metrics_scope_projects.delete

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

dogcp_cloud_monitoring.alert_policies.deleteconfirm_policy: human

Projects alert policies: delete?

intent: the user asked me to projects alert policies: delete

run suspended · waiting for a named person · key gcp-cloud-monitoring-agent cannot confirm itself

In the console, or from an emailed signed link.

a key for this connector

account {  op: "keys.create", name: "gcp-cloud-monitoring-agent",  allowed_actions: ["gcp_cloud_monitoring.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "gcp_cloud_monitoring.alert_policies.delete", approver: "[email protected]" },    { match: "gcp_cloud_monitoring.services.delete", approver: "[email protected]" },    { match: "gcp_cloud_monitoring.notification_channels.delete", approver: "[email protected]" }  ]}

Illustrative. Scoped to Google Cloud Monitoring only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What Google Cloud Monitoring costs on actionlake.

Every Google Cloud Monitoring action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Google Cloud Monitoring refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

1upstream call per actionall 73 Google Cloud Monitoring actions
18actions pageeach page of a long list is one call
33reads can be cacheda cache hit costs nothing
100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every Google Cloud Monitoring action.

73 actions by area: the id your agent calls, what it does, and its effect.

Notification channels8

gcp_cloud_monitoring.notification_channels.createProjects notification channels: createwrite
gcp_cloud_monitoring.notification_channels.deleteProjects notification channels: deletedestructive
gcp_cloud_monitoring.notification_channels.getProjects notification channels: getread
gcp_cloud_monitoring.notification_channels.get_verification_codeProjects notification channels: get verification codewrite
gcp_cloud_monitoring.notification_channels.listProjects notification channels: listread
gcp_cloud_monitoring.notification_channels.patchProjects notification channels: patchwrite
gcp_cloud_monitoring.notification_channels.send_verification_codeProjects notification channels: send verification codewrite
gcp_cloud_monitoring.notification_channels.verifyProjects notification channels: verifywrite

Alert policies5

gcp_cloud_monitoring.alert_policies.createProjects alert policies: createwrite
gcp_cloud_monitoring.alert_policies.deleteProjects alert policies: deletedestructive
gcp_cloud_monitoring.alert_policies.getProjects alert policies: getread
gcp_cloud_monitoring.alert_policies.listProjects alert policies: listread
gcp_cloud_monitoring.alert_policies.patchProjects alert policies: patchwrite

Dashboards5

gcp_cloud_monitoring.dashboards.createProjects dashboards: createwrite
gcp_cloud_monitoring.dashboards.deleteProjects dashboards: deletedestructive
gcp_cloud_monitoring.dashboards.getProjects dashboards: getread
gcp_cloud_monitoring.dashboards.listProjects dashboards: listread
gcp_cloud_monitoring.dashboards.patchProjects dashboards: patchwrite

Groups5

gcp_cloud_monitoring.groups.createProjects groups: createwrite
gcp_cloud_monitoring.groups.deleteProjects groups: deletedestructive
gcp_cloud_monitoring.groups.getProjects groups: getread
gcp_cloud_monitoring.groups.listProjects groups: listread
gcp_cloud_monitoring.groups.updateProjects groups: updatewrite

Prometheus5

gcp_cloud_monitoring.prometheus.labelsProjects location prometheus api v1: labelsread
gcp_cloud_monitoring.prometheus.queryProjects location prometheus api v1: queryread
gcp_cloud_monitoring.prometheus.query_exemplarsProjects location prometheus api v1: query exemplarsread
gcp_cloud_monitoring.prometheus.query_rangeProjects location prometheus api v1: query rangeread
gcp_cloud_monitoring.prometheus.seriesProjects location prometheus api v1: seriesread

Service level objectives5

gcp_cloud_monitoring.service_level_objectives.createServices service level objectives: createwrite
gcp_cloud_monitoring.service_level_objectives.deleteServices service level objectives: deletedestructive
gcp_cloud_monitoring.service_level_objectives.getServices service level objectives: getread
gcp_cloud_monitoring.service_level_objectives.listServices service level objectives: listread
gcp_cloud_monitoring.service_level_objectives.patchServices service level objectives: patchwrite

Services5

gcp_cloud_monitoring.services.createServices: createwrite
gcp_cloud_monitoring.services.deleteServices: deletedestructive
gcp_cloud_monitoring.services.getServices: getread
gcp_cloud_monitoring.services.listServices: listread
gcp_cloud_monitoring.services.patchServices: patchwrite

Uptime check configs5

gcp_cloud_monitoring.uptime_check_configs.createProjects uptime check configs: createwrite
gcp_cloud_monitoring.uptime_check_configs.deleteProjects uptime check configs: deletedestructive
gcp_cloud_monitoring.uptime_check_configs.getProjects uptime check configs: getread
gcp_cloud_monitoring.uptime_check_configs.listProjects uptime check configs: listread
gcp_cloud_monitoring.uptime_check_configs.patchProjects uptime check configs: patchwrite

Metric descriptors4

gcp_cloud_monitoring.metric_descriptors.createProjects metric descriptors: createwrite
gcp_cloud_monitoring.metric_descriptors.deleteProjects metric descriptors: deletedestructive
gcp_cloud_monitoring.metric_descriptors.getProjects metric descriptors: getread
gcp_cloud_monitoring.metric_descriptors.listProjects metric descriptors: listread

Snoozes4

gcp_cloud_monitoring.snoozes.createProjects snoozes: createwrite
gcp_cloud_monitoring.snoozes.getProjects snoozes: getread
gcp_cloud_monitoring.snoozes.listProjects snoozes: listread
gcp_cloud_monitoring.snoozes.patchProjects snoozes: patchwrite

Time series4

gcp_cloud_monitoring.time_series.createProjects time series: createwrite
gcp_cloud_monitoring.time_series.create_serviceProjects time series: create servicewrite
gcp_cloud_monitoring.time_series.listProjects time series: listread
gcp_cloud_monitoring.time_series.queryProjects time series: queryread

Alerts2

gcp_cloud_monitoring.alerts.getProjects alerts: getread
gcp_cloud_monitoring.alerts.listProjects alerts: listread

Metrics scope projects2

gcp_cloud_monitoring.metrics_scope_projects.createLocations global metrics scopes projects: createwrite
gcp_cloud_monitoring.metrics_scope_projects.deleteLocations global metrics scopes projects: deletedestructive

Metrics scopes2

gcp_cloud_monitoring.metrics_scopes.getLocations global metrics scopes: getread
gcp_cloud_monitoring.metrics_scopes.list_metrics_scopes_by_monitored_projectLocations global metrics scopes: list metrics scopes by monitored projectread

Monitored resource descriptors2

gcp_cloud_monitoring.monitored_resource_descriptors.getProjects monitored resource descriptors: getread
gcp_cloud_monitoring.monitored_resource_descriptors.listProjects monitored resource descriptors: listread

Notification channel descriptors2

gcp_cloud_monitoring.notification_channel_descriptors.getProjects notification channel descriptors: getread
gcp_cloud_monitoring.notification_channel_descriptors.listProjects notification channel descriptors: listread

Collectd time series1

gcp_cloud_monitoring.collectd_time_series.createProjects collectd time series: createwrite

Folders time series1

gcp_cloud_monitoring.folders_time_series.listFolders time series: listread

Group members1

gcp_cloud_monitoring.group_members.listProjects groups members: listread

Operations1

gcp_cloud_monitoring.operations.getOperations: getread

Organizations time series1

gcp_cloud_monitoring.organizations_time_series.listOrganizations time series: listread

Prometheus label1

gcp_cloud_monitoring.prometheus_label.valuesProjects location prometheus api v1 label: valuesread

Prometheus metadata1

gcp_cloud_monitoring.prometheus_metadata.listProjects location prometheus api v1 metadata: listread

Uptime check ips1

gcp_cloud_monitoring.uptime_check_ips.listUptime check ips: listread

Questions

The Google Cloud Monitoring MCP server, answered.

Is there a Google Cloud Monitoring MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 73 Google Cloud Monitoring actions across notification channels, alert policies, dashboards and groups, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Google Cloud Monitoring.

What do I need to connect Google Cloud Monitoring?

Your own Google Cloud Monitoring OAuth app, registered with Google Cloud Monitoring (its client id and client secret), and the access and refresh tokens from one admin sign-in. actionlake has no Google Cloud Monitoring app of its own, so this is not a one-step consent. actionlake renews the access token as it expires. The free call account { op: "connections.requirements", service: "gcp_cloud_monitoring" } lists exactly what to paste.

Can an AI agent delete or change things in Google Cloud Monitoring?

Only if its key allows it, and only with an explicit confirmation. 9 Google Cloud Monitoring actions are destructive, including projects alert policies: delete, services: delete and projects notification channels: delete. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my Google Cloud Monitoring API limit?

actionlake paces every call to the limits in the Google Cloud Monitoring service file: 600 calls a minute per connection. Repeated reads are answered from cache (33 Google Cloud Monitoring actions can be), which never reaches Google Cloud Monitoring.

What does a Google Cloud Monitoring action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (18 Google Cloud Monitoring actions page). Cache hits, searches, dry runs and calls Google Cloud Monitoring refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which Google Cloud Monitoring API does it cover?

The Google Cloud Monitoring (metrics, time series, alert policies, alerts, uptime checks, notification channels, SLOs, dashboards, PromQL) API monitoring v3 (Discovery revision 20261015) + monitoring v1 (Discovery revision 20261015) at monitoring.googleapis.com. It is built from Google Cloud Monitoring's documentation as read on 23 October 2026. 73 actions in 24 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Google Cloud Monitoring data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to 5 minutes, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your Google Cloud Monitoring credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

Give your agent Google Cloud Monitoring today.

Connect Google Cloud Monitoring free See pricing

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.

Google Cloud Monitoring MCP server for AI agents.

Connect Google Cloud Monitoring in three steps.

Add actionlake to Claude.

Connect Google Cloud Monitoring.

Make the first call. Check before a write.

What an AI agent can do in Google Cloud Monitoring.

Notification channels

Alert policies

Dashboards

Groups

Prometheus

Service level objectives

Services

Uptime check configs