Sign in Book a demo
Back to Tools
Productivity & Docs OAuth
Build Your Agent View Google Slides Docs
google-slides logo

Google Slides MCP Tools for AI Agents

Let an agent find decks, inspect slides, create presentations from templates, apply edits, and review or resolve comments.

Available Tools

12 tools available in this integration

GoogleSlides.CommentOnPresentation

Add a comment to a presentation, or reply within an existing comment thread.

GoogleSlides.CreateOrEditPresentation

Create a deck or apply a batch of edits to one, returning created object ids,

GoogleSlides.CreatePresentationComment

Add a comment to a presentation, or reply within an existing comment thread.

GoogleSlides.CreatePresentationFromTemplate

Derive a new on-brand deck from an existing branded deck, preserving its

GoogleSlides.GenerateGoogleFilePickerUrl

Generate a URL where the user grants this app access to specific Drive files.

GoogleSlides.GetPresentation

Return an addressable snapshot of a deck: slide and element object ids,

GoogleSlides.GetSlideThumbnail

Render one slide to a PNG.

GoogleSlides.ListPresentationComments

List a page of comments and their replies on a presentation, newest first.

GoogleSlides.ResolveComment

Close (resolve) or reopen a comment thread on a presentation.

GoogleSlides.SavePresentation

Create a deck or apply a batch of edits to one, returning created object ids,

GoogleSlides.SearchPresentations

Search the user's Drive for presentations, newest first by default.

GoogleSlides.WhoAmI

Return the connected Google account's profile (name, email, picture).

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "find our quarterly planning deck, apply the approved slide changes, and list the object IDs it created." Arcade picks the right Google Slides actions without guessing presentation or slide element IDs.

Up to 100x fewer tokens

Google Slides searches return lightweight presentation metadata by default and render slide images only when asked, so the agent can choose a deck without loading every slide into the model.

Complete the workflow end to end

Find the deck, inspect its slides, render a slide when needed, apply the edits, and review or resolve comments through one toolkit designed around the complete presentation task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Google Slides

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Google Slides, you can implement some of these policies:

Access when tools are listed for a user
  • Hide GoogleSlides.CreateOrEditPresentation from agents unless the roles your IDP marks as presentation owners are active, so unapproved agents cannot overwrite or create decks.
  • Restrict GoogleSlides.CommentOnPresentation to agents operating under your designated communications roles, so drafts cannot publish comments to shared decks without the right audience.
  • Deny GoogleSlides.ResolveComment to everyone outside the roles your IDP marks as project leads, so agents cannot close open review threads without accountable ownership.
  • Limit GoogleSlides.CreatePresentationComment to agents serving your review and communications roles, so unapproved automation cannot add feedback to shared decks.
  • Hide GoogleSlides.SavePresentation from agents outside the roles your IDP marks as deck owners, so they cannot create or overwrite presentations.
Pre-execution before each tool call
  • Require human approval before GoogleSlides.CreateOrEditPresentation runs, so an agent cannot alter an approved deck or create a new one without review.
  • Block GoogleSlides.CreatePresentationFromTemplate when the source deck is outside your approved template library, so an agent cannot generate branded work from an untrusted presentation.
  • Refuse GoogleSlides.CommentOnPresentation when the comment contains credentials, access tokens, or customer data, so an agent cannot publish secrets in a shared deck.
  • Require human approval before GoogleSlides.CreatePresentationComment runs on an external or client-facing deck, so an agent cannot publish review feedback without sign-off.
  • Hold GoogleSlides.SavePresentation for approval when it changes a presentation marked approved or final, so an agent cannot silently alter the version stakeholders reviewed.
Post-execution after the tool returns
  • Redact slide text, hyperlinks, and embedded personal details from GoogleSlides.GetPresentation when the deck is marked confidential before the snapshot reaches the model.
  • Strip commenter email addresses and comment bodies from GoogleSlides.ListPresentationComments for decks under legal hold, so private review discussions do not reach the model.
  • Redact the connected user's email address and profile picture from GoogleSlides.WhoAmI before the agent receives account identity details.

How to use Google Slides with your agent

Pick your MCP client below and follow the setup end to end. Each user authorizes their own Google account before the agent can access their presentations.

Your questions, answered

A Google Slides MCP server exposes presentation capabilities as structured tools an AI agent can call through the Model Context Protocol. After a user authorizes their Google account, the agent can search Drive for decks, inspect slides, add comments, and create or edit presentations.

Google Slides does not ship a first-party MCP server. Arcade hosts the integration and adds user-level OAuth, approval workflows, response redaction, scope controls, and access from MCP-compatible clients.

Arcade agents can search for presentations, inspect slide and element IDs, render slide thumbnails, create decks from branded templates, create or batch-edit presentations, add or reply to comments, and resolve or reopen comment threads.

Arcade requests the Google OAuth permissions required by the actions you enable. Read-only workflows need access to find and read the user's presentations, while creating, editing, commenting, and resolving comments require write access; grant the narrowest permissions that support your workflow.

Yes. Each user authorizes their own Google account through OAuth. Actions run under that user's authorization, so an agent can access only the presentations and permissions that user has approved.

Yes. Contextual Access policies can require human approval before consequential Google Slides actions such as editing a deck, creating a presentation, adding comments, or resolving a comment thread. The call proceeds only after the policy's conditions have been satisfied.

Arcade proxies Google Slides API calls and does not persist presentation content as part of normal tool execution. OAuth credentials are brokered and stored encrypted at rest, and the model never receives raw credentials.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade refreshes access while the user's Google authorization remains valid. If access is revoked, rotated, or can no longer be refreshed, calls stop until the user reconnects their Google account.

Google Slides and Google Drive API quotas and account-level limits apply to calls made through Arcade. The applicable limits depend on the Google project, user, and request volume; Arcade does not remove those Google-enforced quotas.

Ready to actually ship your agent?

Connect your agent to Google Slides with managed OAuth, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the Google Slides Quickstart