Integration

Gamma integration

Gamma creates presentations, documents, webpages and social posts with AI. With this API an agent can generate a gamma from a prompt with the Gamma agent (or with the Classic engine, which also does webpages, multi-page sites and template remixes), edit an existing gamma from an instruction, generate standalone images, search gammas and templates, list themes and folders, read a gamma's metadata, comments and engagement analytics, and archive or delete gammas. Generations, edits and images spend the API key owner's Gamma credits (the completed status reports credits.deducted); reads and searches spend no credits. Plans differ: Free allows 10 cards per gamma and 2 agent jobs in flight, paid plans 100 cards and 10 jobs; agent quality max and the analytics routes need Pro or above. Not exposed: file exports (PDF, PPTX, PNG), because Gamma returns them as download links anyone can open, and the names and emails of viewers, comment authors and gamma authors (not returned). Authentication is an API key (starts with sk-gamma-, created in Gamma under Settings, API Keys) sent in the X-API-KEY header.

Connect Gamma How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Gamma.Built from the 22 Gamma tools below, on the connection you add once.

What you can do with Gamma

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Gamma, 5 operations

archive_gammaArchive gammaPOSTArchives a gamma (it can no longer be edited or exported). Idempotent. Needs edit permission; use the API file id (g_...), not the web URL slug.
delete_gammaDelete gammaDELETEDeletes a gamma for real: it is archived if needed, becomes inaccessible at once and can no longer be read through the API. Needs a workspace admin role (403 otherwise).
edit_gammaEdit gammaPOSTEdits one page of an existing gamma from an instruction. Changes it for real and spends credits. Needs edit permission; one edit per page at a time. Waits for the job and returns the finished result; gives up after 10 minutes.
get_gammaGet gammaGETReturns a gamma's metadata: title, type (regular or template), URL, description, theme, creation and update times, archived flag. Accepts a file id or a gamma.app/docs id.
search_gammasSearch gammasGETSearches the gammas the caller can access by title and body text, or browses them by filters (newest first). Pass q, or at least one of createdBy, updatedAfter, updatedBefore.

Generation, 5 operations

create_agent_generationCreate agent generationPOSTGenerates a new gamma (presentation, document or social post) from a prompt with the Gamma agent. Spends credits. The recommended way to generate. Waits for the job and returns the finished result; gives up after 10 minutes.
create_classic_generationCreate classic generationPOSTGenerates a gamma with the Classic engine (also webpages, multi-page files and sites via pages). Pass inputText or pages. Spends credits per card and image. Waits for the job and returns the finished result; gives up after 10 minutes.
create_classic_generation_from_templateCreate classic generation from templatePOSTGenerates a gamma from a workspace template with the Classic engine, keeping its structure unless the prompt asks otherwise. Spends credits. Waits for the job and returns the finished result; gives up after 10 minutes.
get_agent_generation_statusGet agent generation statusGETReturns the status of an agent generation started by create_agent_generation: pending (with progress), completed (gamma.gammaId, gamma.gammaUrl, summary, credits) or failed (error.reason).
get_classic_generation_statusGet classic generation statusGETReturns the status of a Classic generation: pending, completed (gammaId, gammaUrl, credits, per-page results) or failed (error).

Image, 3 operations

archive_imageArchive imagePOSTRemoves a generated image from the workspace media library; the file itself stays and existing URLs keep working. Idempotent.
create_imageCreate imagePOSTGenerates one standalone on-brand image from a prompt; returns its URL, size and savedMediaId. Spends credits. Waits for the job and returns the finished result; gives up after 10 minutes.
get_image_statusGet image statusGETReturns the status of an image generation: pending, completed (image.url, size, format, savedMediaId, credits) or failed (error).

Viewer analytics, 2 operations

get_gamma_viewer_analyticsGet gamma viewer analyticsGETReturns one signed-in viewer's engagement with a gamma: last open, cards viewed and share of view time per card. Pro plan or above. The viewer's name and email are not returned.
list_gamma_viewer_analyticsList gamma viewer analyticsGETLists per-viewer engagement of a gamma (viewer id, last open, cards viewed), up to 500 viewers, paginated. Pro plan or above. Viewer names and emails are not returned.

Card analytics, 1 operation

get_gamma_card_analyticsGet gamma card analyticsGETReturns per-card engagement of a gamma: view time in seconds and share of viewers for each card, in card order. Pro plan or above; data refreshes about hourly.

Comment, 1 operation

list_gamma_commentsList gamma commentsGETLists the comment threads on a gamma with their replies, cursor-paginated. Use updatedSince to fetch only threads with new activity. Author names are not returned, only author ids.

Edit, 1 operation

get_edit_statusGet edit statusGETReturns the status of an edit started by edit_gamma: pending, completed (result.summary, credits) or failed (error.reason; a failed edit may be partly applied, so check the gamma before retrying).

Folder, 1 operation

list_foldersList foldersGETLists the folders the API key's user belongs to in the workspace. Use an id as folderId when generating.

Gamma analytics, 1 operation

get_gamma_analyticsGet gamma analyticsGETReturns a gamma's engagement: total views, unique viewers and editors, card count, last open and 30 days of daily unique viewers. Pro plan or above; scope all needs manage permission, else self.

Template, 1 operation

search_templatesSearch templatesGETSearches workspace templates (usable as gammaId in create_classic_generation_from_template) and official Gamma templates (usable as templateId in create_agent_generation). Without q, browses both.

Theme, 1 operation

list_themesList themesGETLists the themes the workspace can use (standard and custom), with color and tone keywords. Use an id as themeId when generating.

Use Gamma from Claude Code, Cursor or Codex

Connect Gamma in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Gamma operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Gamma

Create your workspace
Sign up free. Nothing to install.
Connect Gamma once
Add your Gamma connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.