Google Slides

Live

OAUTH 2.0

PRESENTATIONS

Every pitch deck, sales presentation, and slide template your team builds lives in Google Slides. Google Slides MCP gives your agent authenticated access to presentations scoped to the user who authorized it.

  • Acts as the user: Access and write actions stay tied to the Google Slides account that authorized the agent.
  • Credentials stay vaulted: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: User permissions enforced. 90-day audit trail.
Google Slides
agent · Acme Q3
Run
Find all pitch decks updated this week and list the slide count and last editor.
S
gslides_presentations_list
76ms
Presentation agent
5 pitch decks updated this week. Acme Enterprise deck (18 slides, Sarah, Oct 29), Globex Q4 deck (12 slides, James, Oct 28), Initech demo (9 slides, Maria, Oct 27), Umbrella renewal (15 slides, David, Oct 26), Stark intro (7 slides, Lisa, Oct 25).
Sources: 5 presentations, this week
googleslidesmcp
5 presentations
18:29
Message Claude...

Tools your presentation agent reaches for on Google Slides, scoped per user.

CALL ANY TOOL
Get slides and layouts, list presentations, replace text, and create new decks.
gslides_presentation_get
Get presentation
Retrieve a presentation's slides, layouts, and notes.
Parameters
Name
Type
Required
Description
presentation_id
string
Required
Google Slides presentation ID
gslides_presentations_list
List presentations
gslides_slide_get
Get slide
gslides_presentation_update
Update presentation
gslides_presentation_create
Create presentation
Build your Agent
Drop the toolkit in, point it at the user, and your presentation agent can use Google Slides from the first run.
import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["googleslides"], toolNames: ["gslides_presentation_get", "gslides_presentations_list", "gslides_slide_get"] },
pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
name: t.tool.definition.name,
description: t.tool.definition.description,
schema: z.object({}).passthrough(),
func: async (args) => {
const { data } = await sk.tools.executeTool({
toolName: t.tool.definition.name,
identifier: "user_123",
params: args,
});
return JSON.stringify(data);
},
}));

const agent = createReactAgent({ llm, tools: lcTools });
import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["googleslides"], toolNames: ["gslides_presentation_get", "gslides_presentations_list", "gslides_slide_get"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
type: "function",
function: {
name: t.tool.definition.name,
description: t.tool.definition.description,
parameters: t.tool.definition.input_schema,
},
}));

const resp = await openai.responses.create({
model: "gpt-4o", input: prompt, tools: llmTools,
});
import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
filter: { connectionNames: ["googleslides"], toolNames: ["gslides_presentation_get", "gslides_presentations_list", "gslides_slide_get"] },
pageSize: 100,
});

const llmTools = tools.map((t) => ({
name: t.tool.definition.name,
description: t.tool.definition.description,
input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
model: "claude-sonnet-4-6", max_tokens: 1024,
tools: llmTools,
messages: [{ role: "user", content: prompt }],
});
import { Agent } from "@google/adk/agents";
import {
MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
connectionParams: new StreamableHTTPConnectionParams({
url: "https://mcp.scalekit.com/googleslides",
headers: { Authorization: `Bearer ${userScopedToken}` },
}),
});

const agent = new Agent({
name: "agent", model: "gemini-2.0-flash",
tools: await toolset.getTools(),
});
Try these prompts
Paste any prompt into your agent to start using Google Slides.
Search & recall
Copy the prompt
Copied
List all presentations updated this week.
Copy the prompt
Copied
Get the slides in [presentation name].
Copy the prompt
Copied
Find decks with [keyword] in the title.
Copy the prompt
Copied
Show me all presentations shared with [email].
Action & editing
Copy the prompt
Copied
Replace [old text] with [new text] in [presentation].
Copy the prompt
Copied
Add a slide to [presentation] with title [title].
Copy the prompt
Copied
Create a new presentation titled [title].
Copy the prompt
Copied
Get the speaker notes on slide [number] of [presentation].
Reporting & audits
Copy the prompt
Copied
How many slides does [deck name] have?
Copy the prompt
Copied
List all decks older than 6 months.
Copy the prompt
Copied
Find presentations with no speaker notes.
Copy the prompt
Copied
Compare slides in [deck A] vs [deck B].
SEE HOW AUTH WORKS
Users authorize Google Slides once. Their credentials stay vaulted, every call is checked, and every action is logged.
1
Authorize
Your user connects
Google Slides
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Google Slides
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Google Slides
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Google Slides
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
Same per-user auth pattern across other presentation agents and MCP connectors. Working code, live demos, fork what fits.
ENGINEERING
Engineering standup agent
Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.
SALES
Sales call prep agent
Pull Granola notes and Attio contact history to draft a pre-call brief before every sales meeting. Zero rep input.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
Other connector libraries treat auth as a demo afterthought. Scalekit starts with user identity, scope enforcement, and audit.
01.
Shared tokens break per-user analytics
A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.
// shared token
 audit → bot_service_account
 user_filter → broken

 // scalekit
 audit → user_abc
 scope → enforced ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Google Slides today. Others tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions

Does the agent access Google Slides as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Google Slides oauth 2.0 stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Google Slides?
Yes. Pass a tool name filter to listScopedTools so the presentation agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Google Slides.

What happens when a user revokes Google Slides access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Can the agent export a deck the owner has restricted from download?
No. Export permissions follow the presentation's sharing settings. If the owner has disabled download for viewers, the agent respects that restriction without exception.

Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""googleslides"": {
""url"": ""https://mcp.scalekit.com/googleslides"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.googleslides]
url = ""https://mcp.scalekit.com/googleslides""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""googleslides"": {
""url"": ""https://mcp.scalekit.com/googleslides"",
""type"": ""http""
}
}
}