Connectors · MSP & PSA

Google Cloud Resource Manager MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to Google Cloud Resource Manager and the rest of your systems. It gives your agent 92 Google Cloud Resource Manager actions (46 reads, 29 writes and 17 that wait for a confirmation) and holds the Google Cloud Resource Manager credential itself, so the agent never does. It paces Google Cloud Resource Manager's limits and records every call. Connecting Google Cloud Resource Manager needs your own Google Cloud Resource Manager OAuth app and one admin sign-in.

Connect Google Cloud Resource Manager 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

92actionsin one signed file
46readlook, never change
29writecreate and update
17wait for a yesdestructive, confirmed first

Set up

Connect Google Cloud Resource Manager 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 Resource Manager.
OAuth 2.0, authorization code with PKCE. You register your own OAuth app with Google Cloud Resource Manager, 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 Resource Manager needs an OAuth app of your own, registered in its developer portal. actionlake has no Google Cloud Resource Manager 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 Resource Manager API…
- client_secretGoogle OAuth client secret
```
account { op: "connections.requirements", service: "gcp_resource_manager" }
# 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_resource_manager.folders.search" }# folders: search · read · 1 upstream callcheck { action: "gcp_resource_manager.folders.delete", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

Google Cloud Resource Manager at a glance

Sign-in: OAuth 2.0, authorization code with PKCE. You register your own OAuth app with Google Cloud Resource Manager, 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 Resource Manager (organizations, folders, projects, tags, liens, IAM policies) API cloudresourcemanager v3 (Discovery revision 20261018)cloudresourcemanager.googleapis.com
Built from: Google Cloud Resource Manager's documentation, read 23 October 2026cloudresourcemanager.googleapis.com cloud.google.com
Service file: Version 1.0.0, signed (Ed25519)
Cached reads: 45 of 46 reads, for up to 5 minutes; a write clears what it affects
Shared entities: 2, so ask can line Google Cloud Resource Manager 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 Resource Manager.

92 actions in 19 areas. Every one carries its effect, so a key can allow the reads and hold the rest.

46readlook, never change
29writecreate and update
17destructivewait for a confirmation

Folders
13
6 read · 5 write · 2 destructive
Folders: list · Folders: search · Folders: create · Folders: patch
Projects
11
5 read · 4 write · 2 destructive
Projects: create · Projects: list · Projects: search · Projects: test iam permissions
Tag keys
9
5 read · 2 write · 2 destructive
Tag keys: create · Tag keys: list · Tag keys: test iam permissions · Tag keys: get
Tag values
9
5 read · 2 write · 2 destructive
Tag values: create · Tag values: list · Tag values: test iam permissions · Tag values: get
Organizations
7
5 read · 1 write · 1 destructive
Organizations: get · Organizations: search · Organizations: test iam permissions · Organizations: get boundary config
Folders boundaries
5
2 read · 2 write · 1 destructive
Folders boundaries: create · Folders boundaries: list · Folders boundaries: get · Folders boundaries: delete
Folders capability configs
5
2 read · 2 write · 1 destructive
Folders capability configs: create · Folders capability configs: list · Folders capability configs: get · Folders capability configs: delete
Organizations boundaries
5
2 read · 2 write · 1 destructive
Organizations boundaries: create · Organizations boundaries: list · Organizations boundaries: get · Organizations boundaries: delete

11 more areas · 28 actions

Organizations capability configs 5
Projects capability configs 5
Liens 4
Tag bindings 3
Tag values tag holds 3
Folders capabilities 2
Locations tag binding collections 2
Effective tags 1
Locations effective tag binding collections 1
Operations 1
Resources 1

Top actions

The Google Cloud Resource Manager API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 7 of Google Cloud Resource Manager's 9 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_resource_manager.folders.list`Folders: list	Lists the folders that are direct descendants of supplied parent resource.	read	`identity.organizational_unit.list`7 connectors
`gcp_resource_manager.folders.search`Folders: search	Search for folders that match specific filter criteria.	read	this connector
`gcp_resource_manager.folders.delete`Folders: delete	Requests deletion of a folder.	destructive	`identity.organizational_unit.delete`7 connectors
`gcp_resource_manager.organizations.get`Organizations: get	Fetches an organization resource identified by the specified resource name.	read	`platform.tenant.get`86 connectors
`gcp_resource_manager.organizations.search`Organizations: search	Searches organization resources that are visible to the user and satisfy the specified filter.	read	`platform.tenant.search`4 connectors
`gcp_resource_manager.liens.list`Liens: list	List all Liens applied to the `parent` resource.	read	this connector
`gcp_resource_manager.liens.create`Liens: create	Create a Lien which applies to the resource denoted by the `parent` field.	write	this connector
`gcp_resource_manager.projects.list`Projects: list	Lists projects that are direct children of the specified folder or organization resource.	read	this connector
`gcp_resource_manager.tag_keys.list`Tag keys: list	Lists all TagKeys for a parent resource.	read	this connector
`gcp_resource_manager.projects.create`Projects: create	Request that a new project be created.	write	this connector
`gcp_resource_manager.tag_keys.create`Tag keys: create	Creates a new TagKey.	write	this connector
`gcp_resource_manager.tag_values.list`Tag values: list	Lists all TagValues for a specific TagKey.	read	this connector

Try it

Prompts to paste into Claude.

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

Readread
Folders: search in Google Cloud Resource Manager and tell me what stands out.
callsgcp_resource_manager.folders.search
Writewrite
Liens: create in Google Cloud Resource Manager. Show me exactly what you will send before you save it.
callsgcp_resource_manager.liens.create

Governance for Google Cloud Resource Manager

Destructive actions wait for a yes.

17 Google Cloud Resource Manager actions are destructive. These are all of them:

Folders: deletegcp_resource_manager.folders.delete
Liens: deletegcp_resource_manager.liens.delete
Projects: deletegcp_resource_manager.projects.delete
Tag keys: deletegcp_resource_manager.tag_keys.delete
Tag values: deletegcp_resource_manager.tag_values.delete
Tag bindings: deletegcp_resource_manager.tag_bindings.delete
Folders: set iam policygcp_resource_manager.folders.set_iam_policy
Projects: set iam policygcp_resource_manager.projects.set_iam_policy
Tag keys: set iam policygcp_resource_manager.tag_keys.set_iam_policy
Tag values: set iam policygcp_resource_manager.tag_values.set_iam_policy
Organizations: set iam policygcp_resource_manager.organizations.set_iam_policy
Folders boundaries: deletegcp_resource_manager.folders_boundaries.delete
Tag values tag holds: deletegcp_resource_manager.tag_values_tag_holds.delete
Organizations boundaries: deletegcp_resource_manager.organizations_boundaries.delete
Folders capability configs: deletegcp_resource_manager.folders_capability_configs.delete
Projects capability configs: deletegcp_resource_manager.projects_capability_configs.delete
Organizations capability configs: deletegcp_resource_manager.organizations_capability_configs.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_resource_manager.folders.deleteconfirm_policy: human

Folders: delete?

intent: the user asked me to folders: delete

run suspended · waiting for a named person · key gcp-resource-manager-agent cannot confirm itself

In the console, or from an emailed signed link.

a key for this connector

account {  op: "keys.create", name: "gcp-resource-manager-agent",  allowed_actions: ["gcp_resource_manager.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "gcp_resource_manager.folders.delete", approver: "[email protected]" },    { match: "gcp_resource_manager.liens.delete", approver: "[email protected]" },    { match: "gcp_resource_manager.projects.delete", approver: "[email protected]" }  ]}

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

Cost

What Google Cloud Resource Manager costs on actionlake.

Every Google Cloud Resource Manager action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call Google Cloud Resource Manager 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 92 Google Cloud Resource Manager actions
16actions pageeach page of a long list is one call
45reads 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 Resource Manager action.

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

Folders13

gcp_resource_manager.folders.createFolders: createwrite
gcp_resource_manager.folders.deleteFolders: deletedestructive
gcp_resource_manager.folders.getFolders: getread
gcp_resource_manager.folders.get_boundary_configFolders: get boundary configread
gcp_resource_manager.folders.get_iam_policyFolders: get iam policyread
gcp_resource_manager.folders.listFolders: listread
gcp_resource_manager.folders.moveFolders: movewrite
gcp_resource_manager.folders.patchFolders: patchwrite
gcp_resource_manager.folders.searchFolders: searchread
gcp_resource_manager.folders.set_iam_policyFolders: set iam policydestructive
gcp_resource_manager.folders.test_iam_permissionsFolders: test iam permissionsread
gcp_resource_manager.folders.undeleteFolders: undeletewrite
gcp_resource_manager.folders.update_boundary_configFolders: update boundary configwrite

Projects11

gcp_resource_manager.projects.createProjects: createwrite
gcp_resource_manager.projects.deleteProjects: deletedestructive
gcp_resource_manager.projects.getProjects: getread
gcp_resource_manager.projects.get_iam_policyProjects: get iam policyread
gcp_resource_manager.projects.listProjects: listread
gcp_resource_manager.projects.moveProjects: movewrite
gcp_resource_manager.projects.patchProjects: patchwrite
gcp_resource_manager.projects.searchProjects: searchread
gcp_resource_manager.projects.set_iam_policyProjects: set iam policydestructive
gcp_resource_manager.projects.test_iam_permissionsProjects: test iam permissionsread
gcp_resource_manager.projects.undeleteProjects: undeletewrite

Tag keys9

gcp_resource_manager.tag_keys.createTag keys: createwrite
gcp_resource_manager.tag_keys.deleteTag keys: deletedestructive
gcp_resource_manager.tag_keys.getTag keys: getread
gcp_resource_manager.tag_keys.get_iam_policyTag keys: get iam policyread
gcp_resource_manager.tag_keys.get_namespacedTag keys: get namespacedread
gcp_resource_manager.tag_keys.listTag keys: listread
gcp_resource_manager.tag_keys.patchTag keys: patchwrite
gcp_resource_manager.tag_keys.set_iam_policyTag keys: set iam policydestructive
gcp_resource_manager.tag_keys.test_iam_permissionsTag keys: test iam permissionsread

Tag values9

gcp_resource_manager.tag_values.createTag values: createwrite
gcp_resource_manager.tag_values.deleteTag values: deletedestructive
gcp_resource_manager.tag_values.getTag values: getread
gcp_resource_manager.tag_values.get_iam_policyTag values: get iam policyread
gcp_resource_manager.tag_values.get_namespacedTag values: get namespacedread
gcp_resource_manager.tag_values.listTag values: listread
gcp_resource_manager.tag_values.patchTag values: patchwrite
gcp_resource_manager.tag_values.set_iam_policyTag values: set iam policydestructive
gcp_resource_manager.tag_values.test_iam_permissionsTag values: test iam permissionsread

Organizations7

gcp_resource_manager.organizations.getOrganizations: getread
gcp_resource_manager.organizations.get_boundary_configOrganizations: get boundary configread
gcp_resource_manager.organizations.get_iam_policyOrganizations: get iam policyread
gcp_resource_manager.organizations.searchOrganizations: searchread
gcp_resource_manager.organizations.set_iam_policyOrganizations: set iam policydestructive
gcp_resource_manager.organizations.test_iam_permissionsOrganizations: test iam permissionsread
gcp_resource_manager.organizations.update_boundary_configOrganizations: update boundary configwrite

Folders boundaries5

gcp_resource_manager.folders_boundaries.createFolders boundaries: createwrite
gcp_resource_manager.folders_boundaries.deleteFolders boundaries: deletedestructive
gcp_resource_manager.folders_boundaries.getFolders boundaries: getread
gcp_resource_manager.folders_boundaries.listFolders boundaries: listread
gcp_resource_manager.folders_boundaries.patchFolders boundaries: patchwrite

Folders capability configs5

gcp_resource_manager.folders_capability_configs.createFolders capability configs: createwrite
gcp_resource_manager.folders_capability_configs.deleteFolders capability configs: deletedestructive
gcp_resource_manager.folders_capability_configs.getFolders capability configs: getread
gcp_resource_manager.folders_capability_configs.listFolders capability configs: listread
gcp_resource_manager.folders_capability_configs.patchFolders capability configs: patchwrite

Organizations boundaries5

gcp_resource_manager.organizations_boundaries.createOrganizations boundaries: createwrite
gcp_resource_manager.organizations_boundaries.deleteOrganizations boundaries: deletedestructive
gcp_resource_manager.organizations_boundaries.getOrganizations boundaries: getread
gcp_resource_manager.organizations_boundaries.listOrganizations boundaries: listread
gcp_resource_manager.organizations_boundaries.patchOrganizations boundaries: patchwrite

Organizations capability configs5

gcp_resource_manager.organizations_capability_configs.createOrganizations capability configs: createwrite
gcp_resource_manager.organizations_capability_configs.deleteOrganizations capability configs: deletedestructive
gcp_resource_manager.organizations_capability_configs.getOrganizations capability configs: getread
gcp_resource_manager.organizations_capability_configs.listOrganizations capability configs: listread
gcp_resource_manager.organizations_capability_configs.patchOrganizations capability configs: patchwrite

Projects capability configs5

gcp_resource_manager.projects_capability_configs.createProjects capability configs: createwrite
gcp_resource_manager.projects_capability_configs.deleteProjects capability configs: deletedestructive
gcp_resource_manager.projects_capability_configs.getProjects capability configs: getread
gcp_resource_manager.projects_capability_configs.listProjects capability configs: listread
gcp_resource_manager.projects_capability_configs.patchProjects capability configs: patchwrite

Liens4

gcp_resource_manager.liens.createLiens: createwrite
gcp_resource_manager.liens.deleteLiens: deletedestructive
gcp_resource_manager.liens.getLiens: getread
gcp_resource_manager.liens.listLiens: listread

Tag bindings3

gcp_resource_manager.tag_bindings.createTag bindings: createwrite
gcp_resource_manager.tag_bindings.deleteTag bindings: deletedestructive
gcp_resource_manager.tag_bindings.listTag bindings: listread

Tag values tag holds3

gcp_resource_manager.tag_values_tag_holds.createTag values tag holds: createwrite
gcp_resource_manager.tag_values_tag_holds.deleteTag values tag holds: deletedestructive
gcp_resource_manager.tag_values_tag_holds.listTag values tag holds: listread

Folders capabilities2

gcp_resource_manager.folders_capabilities.getFolders capabilities: getread
gcp_resource_manager.folders_capabilities.patchFolders capabilities: patchwrite

Locations tag binding collections2

gcp_resource_manager.locations_tag_binding_collections.getLocations tag binding collections: getread
gcp_resource_manager.locations_tag_binding_collections.patchLocations tag binding collections: patchwrite

Effective tags1

gcp_resource_manager.effective_tags.listEffective tags: listread

Locations effective tag binding collections1

gcp_resource_manager.locations_effective_tag_binding_collections.getLocations effective tag binding collections: getread

Operations1

gcp_resource_manager.operations.getOperations: getread

Resources1

gcp_resource_manager.resources.fetch_resource_semanticsV3: fetch resource semanticsread

Questions

The Google Cloud Resource Manager MCP server, answered.

Is there a Google Cloud Resource Manager MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 92 Google Cloud Resource Manager actions across folders, projects, tag keys and tag values, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by Google Cloud Resource Manager.

What do I need to connect Google Cloud Resource Manager?

Your own Google Cloud Resource Manager OAuth app, registered with Google Cloud Resource Manager (its client id and client secret), and the access and refresh tokens from one admin sign-in. actionlake has no Google Cloud Resource Manager 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_resource_manager" } lists exactly what to paste.

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

Only if its key allows it, and only with an explicit confirmation. 17 Google Cloud Resource Manager actions are destructive, including folders: delete, liens: delete and projects: 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 Resource Manager API limit?

actionlake paces every call to the limits in the Google Cloud Resource Manager service file: 600 calls a minute per connection. Repeated reads are answered from cache (45 Google Cloud Resource Manager actions can be), which never reaches Google Cloud Resource Manager.

What does a Google Cloud Resource Manager action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (16 Google Cloud Resource Manager actions page). Cache hits, searches, dry runs and calls Google Cloud Resource Manager 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 Resource Manager API does it cover?

The Google Cloud Resource Manager (organizations, folders, projects, tags, liens, IAM policies) API cloudresourcemanager v3 (Discovery revision 20261018) at cloudresourcemanager.googleapis.com. It is built from Google Cloud Resource Manager's documentation as read on 23 October 2026. 92 actions in 19 areas, each one in the signed service file (version 1.0.0).

Does actionlake keep my Google Cloud Resource Manager 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 Resource Manager 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 Resource Manager today.

Connect Google Cloud Resource Manager free See pricing

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

Google Cloud Resource Manager MCP server for AI agents.

Connect Google Cloud Resource Manager in three steps.

Add actionlake to Claude.

Connect Google Cloud Resource Manager.

Make the first call. Check before a write.

What an AI agent can do in Google Cloud Resource Manager.

Folders

Projects

Tag keys

Tag values

Organizations

Folders boundaries

Folders capability configs

Organizations boundaries