Gamma connector for AI agents

Tools your presentations agent reaches for on Gamma, scoped per user.

CALL ANY TOOL

23 tools for presentations in Gamma: generate Gammas and images from prompts or templates, edit pages, export to PDF, PPTX, or PNG, search content, and read engagement analytics.

gamma_archive_gamma

Archive gamma

Archive a Gamma document. Archiving an already archived Gamma succeeds. Returns gammaId and archived. Use to retire a Gamma without deleting it. Find IDs with gamma_search_gammas.

Parameters

Name

Type

Required

Description

gamma_id

string

Required

ID of the Gamma to archive.

gamma_archive_image

Archive image

gamma_create_agent_generation

Create agent generation

Start an asynchronous Gamma agent generation from a natural-language prompt, with optional source URLs and a template. Returns generationId (prefixed gen_), status and warnings; the Gamma is not ready yet. Use when you want the Gamma agent to research and build from a brief. Use gamma_create_generation to shape the output from your own text. Poll gamma_get_agent_generation with the generationId. Spends credits and requires a paid Gamma plan with API access.

Parameters

Name

Type

Required

Description

prompt

string

Required

The brief describing what to generate, up to 400000 characters. Example: "A 10-slide investor update on our Q3 growth".

additional_instructions

string

Optional

Extra guidance such as tone, audience, language or style, up to 5000 characters.

disable_connectors

boolean

Optional

Set true to stop this run from using workspace connectors such as Notion or Slack.

export_as

string

Optional

Export the finished Gamma automatically after generation. The download link appears as exportUrl when the generation status is completed. One of: `pdf`, `png`, `pptx`.

external_access

string

Optional

Access level for anyone outside the workspace who opens the shared link. One of: `comment`, `edit`, `noAccess`, `view`.

folder_id

string

Optional

ID of the folder to place the new Gamma in. Get IDs from gamma_list_folders.

format

string

Optional

Output format: presentation (default), document or social. webpage is not supported by the agent. One of: `document`, `presentation`, `social`.

num_cards

integer

Optional

Soft target for the number of cards, from 1 to 100. A value above the plan limit is rejected.

quality

string

Optional

Quality preset: lite, standard or max. The max preset needs a plan that includes it and can use more credits. One of: `lite`, `max`, `standard`.

share_email_access

string

Optional

Permission level for the addresses in share_with_emails. Only used when share_with_emails is also provided. One of: `comment`, `edit`, `fullAccess`, `view`.

share_with_emails

array

Optional

Email addresses to share the new Gamma with. Pair with share_email_access to choose their permission level.

source_urls

array

Optional

Up to 10 http or https URLs the agent should read as source material. This is guidance; unreadable URLs are skipped.

template_id

string

Optional

Optional starting point: the ID of a workspace template, a Gamma in the workspace or an official Gamma template. Find IDs with gamma_search_templates.

theme_id

string

Optional

ID of the theme to apply. Get IDs from gamma_list_themes.

workspace_access

string

Optional

Default access level for members of the workspace on the new Gamma. One of: `comment`, `edit`, `fullAccess`, `noAccess`, `view`.

gamma_create_from_template

Create from template

Start an asynchronous generation that adapts an existing single-page Gamma used as a template. Returns generationId immediately; the new Gamma is not ready yet. Use gamma_create_from_template to remix a template Gamma, found with gamma_search_templates or gamma_search_gammas. Use gamma_create_generation to build from text without a template. Poll gamma_get_generation with the returned generationId. Spends credits and requires a paid Gamma plan with API access.

Parameters

Name

Type

Required

Description

gamma_id

string

Required

File ID of the Gamma to use as the template. The Gamma must contain exactly one page.

prompt

string

Required

Instructions describing what to generate from the template (1 to 400000 characters). Example: "Adapt this pitch for a healthcare audience".

export_as

string

Optional

Export the finished Gamma automatically after generation. The download link appears as exportUrl when the generation status is completed. One of: `pdf`, `png`, `pptx`.

external_access

string

Optional

Access level for anyone outside the workspace who opens the shared link. One of: `comment`, `edit`, `noAccess`, `view`.

folder_id

string

Optional

ID of the folder to place the new Gamma in. Get IDs from gamma_list_folders.

image_model

string

Optional

Image model to use for AI generated images. See the Gamma image models reference for accepted values.

image_style

string

Optional

Style description for generated images, up to 5000 characters. Example: "clean photography".

share_email_access

string

Optional

Permission level for the addresses in share_with_emails. Only used when share_with_emails is also provided. One of: `comment`, `edit`, `fullAccess`, `view`.

share_with_emails

array

Optional

Email addresses to share the new Gamma with. Pair with share_email_access to choose their permission level.

theme_id

string

Optional

ID of the theme to apply. Get IDs from gamma_list_themes.

title

string

Optional

Custom title for the new Gamma (1 to 500 characters). When empty, Gamma generates a title.

workspace_access

string

Optional

Default access level for members of the workspace on the new Gamma. One of: `comment`, `edit`, `fullAccess`, `noAccess`, `view`.

gamma_create_generation

Create generation

Start an asynchronous Gamma generation from text, producing a presentation, document, webpage or social post. Returns generationId immediately; the Gamma is not ready yet. Use gamma_create_generation when you have text or a topic. Use gamma_create_from_template to adapt an existing Gamma. Use gamma_create_agent_generation for an agent-driven build from a prompt. Poll gamma_get_generation with the returned generationId. Spends credits and requires a paid Gamma plan with API access.

Parameters

Name

Type

Required

Description

input_text

string

Required

Text to generate from: a topic, an outline or full content (1 to 400000 characters). Example: "Quarterly sales review for Q3 2026 with revenue, wins and risks".

additional_instructions

string

Optional

Extra guidance for the AI such as structure or emphasis, up to 5000 characters. Example: "Keep each slide to three bullet points".

audience

string

Optional

Target audience of the content, up to 500 characters. Example: "enterprise buyers".

card_dimensions

string

Optional

Aspect ratio or page size of each card: 16x9, 4x3, 1x1, 4x5, 9x16, a4, letter, fluid or pageless. Valid values depend on the format. One of: `16x9`, `1x1`, `4x3`, `4x5`, `9x16`, `a4`, `fluid`, `letter`, `pageless`.

card_split

string

Optional

How Gamma splits the content into cards: auto lets Gamma decide, inputTextBreaks splits at the horizontal rules (---) you put in input_text. One of: `auto`, `inputTextBreaks`.

export_as

string

Optional

Export the finished Gamma automatically after generation. The download link appears as exportUrl when the generation status is completed. One of: `pdf`, `png`, `pptx`.

external_access

string

Optional

Access level for anyone outside the workspace who opens the shared link. One of: `comment`, `edit`, `noAccess`, `view`.

folder_id

string

Optional

ID of the folder to place the new Gamma in. Get IDs from gamma_list_folders.

format

string

Optional

Output format of the Gamma: presentation, document, webpage or social. One of: `document`, `presentation`, `social`, `webpage`.

image_model

string

Optional

Image model to use when image_source is aiGenerated, for example flux-2-pro, gemini-3-pro-image or recraft-v4. See the Gamma image models reference for accepted values.

image_source

string

Optional

Where images come from: aiGenerated, webAllImages, webFreeToUse, webFreeToUseCommercially, pexels, giphy, pictographic, themeAccent, placeholder or noImages. One of: `aiGenerated`, `giphy`, `noImages`, `pexels`, `pictographic`, `placeholder`, `themeAccent`, `webAllImages`, `webFreeToUse`, `webFreeToUseCommercially`.

image_style

string

Optional

Style description for AI generated images, up to 5000 characters. Example: "minimal flat illustration in blue tones".

language

string

Optional

Language code of the generated content, for example en, es, fr, de, ja, pt-br or zh-cn. See the Gamma output languages reference for the full list.

num_cards

integer

Optional

Target number of cards (slides or sections) to generate, at least 1. Limits depend on the workspace plan.

share_email_access

string

Optional

Permission level for the addresses in share_with_emails. Only used when share_with_emails is also provided. One of: `comment`, `edit`, `fullAccess`, `view`.

share_with_emails

array

Optional

Email addresses to share the new Gamma with. Pair with share_email_access to choose their permission level.

text_amount

string

Optional

How much text to put on each card: brief, medium, detailed or extensive. One of: `brief`, `detailed`, `extensive`, `medium`.

text_mode

string

Optional

How Gamma treats input_text: generate expands a short topic, condense shortens long text, preserve keeps your wording. Use generate for a short topic and preserve for finished copy. One of: `condense`, `generate`, `preserve`.

theme_id

string

Optional

ID of the theme to apply. Get IDs from gamma_list_themes.

title

string

Optional

Custom title for the Gamma (1 to 500 characters). When empty, Gamma generates a title from the content.

tone

string

Optional

Tone or writing style of the generated text, up to 500 characters. Example: "professional and upbeat".

workspace_access

string

Optional

Default access level for members of the workspace on the new Gamma. One of: `comment`, `edit`, `fullAccess`, `noAccess`, `view`.

gamma_create_image

Create image

gamma_edit_gamma

Edit gamma

gamma_export_gamma

Export gamma

gamma_get_agent_generation

Get agent generation

gamma_get_analytics

Get analytics

gamma_get_card_analytics

Get card analytics

gamma_get_edit

Get edit

gamma_get_export

Export get

gamma_get_gamma

Get gamma

gamma_get_generation

Get generation

gamma_get_image

Get image

gamma_get_viewer_analytics

Get viewer analytics

gamma_list_comments

List comments

gamma_list_folders

List folders

gamma_list_themes

List themes

gamma_list_viewer_analytics

List viewer analytics

gamma_search_gammas

Search gammas

gamma_search_templates

Search templates

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Gamma tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["gamma"], toolNames: [
    "gamma_create_generation",
    "gamma_get_generation",
    "gamma_export_gamma"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Create a 10-card deck on our Q4 roadmap and export it as a PDF" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["gamma"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Create a 10-card deck on our Q4 roadmap and export it as a PDF" }],
  tools,
});

// Execute the tool call with the user's vaulted Gamma API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["gamma"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Create a 10-card deck on our Q4 roadmap and export it as a PDF" }],
  tools,
});

// Tool call runs with the user's vaulted Gamma API key
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["gamma"] }, pageSize: 100,
});

const agent = new Agent({
  name: "presentations_agent",
  model: "gemini-2.5-pro",
  instruction: "Gamma tools scoped to this user",
  tools,
});

await agent.run("Create a 10-card deck on our Q4 roadmap and export it as a PDF");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Gamma tool. Click to copy, paste into your agent, done.

Generate

Copy the prompt

Copied

Create a 10-card presentation on our Q4 product roadmap.

Copy the prompt

Copied

Build a webpage from these launch notes using our brand theme.

Copy the prompt

Copied

Generate a cover image of a city skyline at dusk for the sales deck.

Edit and export

Copy the prompt

Copied

Export the Q3 board deck as a PDF.

Copy the prompt

Copied

Shorten the text on the pricing page of the Sales Kickoff deck.

Copy the prompt

Copied

Archive last year's onboarding deck.

Analytics

Copy the prompt

Copied

Which cards in the investor update got the most view time?

Copy the prompt

Copied

List everyone who viewed the partner proposal and how many cards they saw.

Copy the prompt

Copied

Show open comment threads on the launch deck.

SEE HOW AUTH WORKS

Each user connects their own Gamma API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Gamma

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

Store

Their

Gamma

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

Resolve

When your agent calls a

Gamma

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

Audit

Every

Gamma

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

See the same per-user auth pattern across other productivity and design connectors.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Gamma API key looks fine in a demo. In production every generated deck and export looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Gamma today. Ten connectors 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 Gamma as the user or through a shared key?

As the user. Each user connects their own Gamma API key once, and Scalekit sends it with every call. Generations, edits, and exports the agent starts are attributed to that user in your audit trail, not a shared service account.

Where is the Gamma API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Gamma?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the search and analytics tools without gamma_archive_gamma or the generation tools, which spend credits. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Gamma 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.

How does the agent know when a Gamma is ready?

Generation, edit, export, and image tools run asynchronously. gamma_create_generation returns a generationId right away, and the agent polls gamma_get_generation until the status is completed. Exports work the same way through gamma_get_export, which returns the download link.