PopMCP
data_studio_Give people, groups or a domain a role on a report or data source (Google's addMembers).
Google Data Studio MCP server for your AI
Ask which dashboards anyone with the link can open, share a client report with a few emails, switch link sharing off, or build a report on a client's own data, from the AI client you already use.
PopMCPGoogle Data Studio
Which of my Data Studio reports can anyone with the link open, and who outside the company has access?
Supported Google Data Studio tools
Every Data Studio API method, asset search and sharing, plus tools that find reports by name, check the sharing of many reports at once and build Linking API report links. Google now calls the product Data Studio again; links on either domain work.
13 tools in the full catalog: 7 read and 6 write. 13 load by default, and the rest are found with tool search.
data_studio_Who has access to one report or data source: the members of each role (OWNER, EDITOR, VIEWER, LINK_VIEWER, LINK_EDITOR) and the etag.
data_studio_Remove people, groups or a domain from every role on a report or data source (Google's revokeAllPermissions).
data_studio_Turn link sharing off, or on for view or edit, for anyone or a domain.
data_studio_Share with people, groups or a domain as viewer or editor.
data_studio_Check the sharing of many assets and flag link sharing and outsiders.
data_studio_Remove people, groups or a domain, saying who really had access.
data_studio_Set the members of one or more roles on a report or data source in one write (Google's permissions.patch).
data_studio_Find data sources by name, owner or who they were shared with, with links.
data_studio_Find reports by name, owner or who they were shared with, with links.
data_studio_One report or data source by id or link: details and who has access, in words.
data_studio_Search the Data Studio reports or data sources the signed-in Google account can see, by title words or filters (owner:me, creator:me, to:/from:email).
data_studio_Build a Linking API link that creates a report from a template on the opener's data.
Connect Google Data Studio to Claude, ChatGPT and Claude Code
Authorize once, then an endpoint your client signs into. Nothing to deploy, and nothing to install on the Google Data Studio side.
Sign in with a Google Workspace or Cloud Identity account. Google only lets apps a Workspace admin has approved use Data Studio's API, so an admin first adds the client ID and the Data Studio scopes under domain-wide delegation in the Admin console. The connect form shows both.
OAuth Client ID
1234567890-abc.apps.googleusercontent.comOAuth Client Secret
••••••••••••3f7aScopes your Workspace super admin authorizes
your-google-data-studio-valueAuthorize PopMCP on Google Data StudioAuthorize
Connections start read-only. Once an owner allows writes, share_with_people, unshare_with_people and set_link_sharing change who can open a report as soon as the AI calls them. Google's API cannot read a report's charts or numbers, and cannot delete anything.
Reach Google Data Studio
Reach other connectors
Teammates on read-only
Drop the PopMCP URL into Claude, ChatGPT, Claude Code, Codex or any other supported client. It signs in through PopMCP with OAuth, so your Google Data Studio credential never leaves the server.
app.popmcp.com/mcp
Claude wants to connectApproveAsk for something harmless before the agent changes anything. Writes run as soon as it calls them, so confirm it reads the right account first.
Which of my Data Studio reports can anyone with the link open, and who outside the company has access?
data_studio_sharing_auditok
Then just ask for the work
“Which of my Data Studio reports can anyone with the link open, and who outside the company has access?”
- sharing_audit
“Find the Q3 client dashboard and share it with ana@client.com as a viewer”
- find_reports
- share_with_people
“Turn link sharing off on every report the audit flags as open to anyone”
- sharing_audit
- set_link_sharing
“Remove the freelancer's access from all of my reports”
- find_reports
- unshare_with_people
“Build a report link from our SEO template for the client's Search Console property client.com”
- find_reports
- build_report_link
Use Google Data Studio from the assistant you already open
One hosted endpoint, registered once per client. The same tools and the same permissions, whichever window the request comes from.
Claude DesktopCustom connector
Add the PopMCP URL under Customize → Connectors and the tools appear in every chat.
Claude WebCustom connector
The same endpoint, registered in the browser. Nothing to install on the machine you are working from.
ChatGPTCustom connector
Register PopMCP as a custom connector, then let ChatGPT read and update the account.
CodexDesktop & CLI
Wire the endpoint into Codex or the Codex CLI when a task needs live business context, not a fixture.
OpenCodeCoding agent
Register the remote MCP server in OpenCode's config for terminal-first and scripted agent runs.
ZCodeDesktop app
Add PopMCP as an MCP server in Z.ai's desktop app and work the account from the same window.
Explore other MCP servers
Every one of them runs on the same hosted endpoint, with the same controls.
FAQ
Google Data Studio MCP server questions
What teams ask before putting Google Data Studio behind an AI client.
Why does Google show Error 400: invalid_scope when I sign in?
Data Studio's API only answers apps that a Google Workspace admin has approved for the organization. Until an admin adds the app's client ID with the Data Studio scopes (Admin console, Security, Access and data control, API controls, Manage domain-wide delegation, Add new), Google refuses the sign-in with that error. After that, people in the organization connect without a consent screen at all. The connect form shows the client ID and the scopes to give your admin.
Can I connect a personal Gmail account?
No. Google opens the Data Studio API only to Google Workspace and Cloud Identity accounts. Reports a personal account owns can still be reached: share them with your Workspace account and connect that one, since every tool covers everything the signed-in account can see.
Can the AI read the charts or numbers inside a report?
No. Google's API covers finding reports and data sources and managing who can open them. It cannot read a report's pages, charts, fields or data, and it cannot create, copy or delete reports. For the numbers, connect the data source itself, such as Google Analytics, Search Console or BigQuery. To create a report, build_report_link makes a Linking API link that copies a template onto the opener's own data.
What does the sharing audit check?
sharing_audit reads the sharing of each report or data source you own, up to a limit you choose, and flags anyone-with-the-link access (worst when it can edit), people and groups outside your organization's email domain, and whole domains. It returns the flagged ones first, with links, and counts the clean ones. set_link_sharing and unshare_with_people fix what it finds.
Is it Data Studio or Data Studio?
Both. Google renamed Looker Studio back to Data Studio in April 2026, and Data Studio Pro is now Data Studio Pro. Nothing about the API or your reports changed, and links on lookerstudio.google.com and datastudio.google.com both work with every tool.
Which Data Studio changes can PopMCP watch?
Five, all by change detection. Across the account: a report created, edited, or moved to the trash. On a report you watch: someone gains or loses access, and link sharing turned on for anyone or a whole domain. A typical use is a message to the team whenever a client report becomes public.
Do I have to run or host the Google Data Studio MCP server myself?
No. PopMCP hosts it and gives you a Streamable HTTP MCP URL. There is nothing to deploy, no callback URL to register, and no infrastructure to keep running or patch.
Which AI clients can use this MCP server?
Any client that supports a remote Streamable HTTP MCP server: Claude Desktop, Claude Web, Claude Code, ChatGPT custom connectors, Codex and the Codex CLI, OpenCode and Z.ai's ZCode, as well as editors such as Cursor, Windsurf and Zed. Your client signs in to PopMCP with OAuth; the provider credential never leaves the server.
How do I connect Google Data Studio to Claude Code?
Connect Google Data Studio in PopMCP first, then run claude mcp add --transport http popmcp https://app.popmcp.com/mcp in a terminal. Inside Claude Code, run /mcp and sign in to PopMCP in the browser window it opens, ticking Google Data Studio on the consent screen. The Google Data Studio tools are then available in that session, and no Google Data Studio credential is stored on your machine.
Do all 13 Google Data Studio tools load by default?
Yes. The Google Data Studio catalog is small enough that all 13 tool definitions load into every conversation, so your AI never has to search for one before it can call it.
What is the difference between a tool and a trigger?
A tool is something your AI calls, and there are 13 here. A trigger is something PopMCP watches for you: 5 Google Data Studio events that can start work on the PopMCP side. Triggers never enter your AI client's context, and none of them ask you to paste a callback URL into Google Data Studio.
Connect Google Data Studio to your AI in minutes
Launch a hosted MCP endpoint for Google Data Studio, keep tool access under control, and start testing real workflow prompts right away.