How to connect a Gamma MCP with Claude Code (4 steps)

Claude Code can generate structured content from any data source: changelog entries, sprint summaries, architecture decisions, incident postmortems. Getting that content into a polished Gamma deck still requires opening a browser, copying the output, and reformatting it by hand.

In other words, the gap between "Claude Code generated this" and "this is a shareable deck" is manual work that happens outside the terminal.

To help your developers create and update Gamma decks directly from generated content in the terminal, we'll show you how to connect Gamma with Merge Agent Handler's Gamma MCP server.

How it works

Merge Agent Handler sits between Claude Code and the Gamma API. You install the Merge CLI, authenticate once, and register the connection with a single command. Agent Handler manages credential storage and API calls to Gamma so you don't keep tokens in your local environment or wire authentication into your codebase.

Here's the command that registers the connection:

merge setup claude-code

Prerequisites

Before getting started, you'll need the following:

• A Merge Agent Handler account
• Claude Code installed (run claude --version to confirm)
• pipx installed (run pipx --version to confirm, or install via pip install pipx)
• A Gamma account with API access enabled

If you want to connect Merge Agent Handler's Gamma MCP with internal or customer-facing agentic products, you can follow the steps in our docs.

1. Install the Merge CLI

Install with pipx: pipx install merge-api

Verify your installation: merge --version

2. Configure the CLI and log in

This links the CLI to your Merge account and authenticates your session: merge login

Once logged in, the CLI is ready to make authorized requests on your behalf.

3. Add Agent Handler to Claude Code

To add Agent Handler to Claude Code, run:

merge setup claude-code

Or register manually with:

claude mcp add 
--transport http agent-handler https://ah-api.merge.dev/mcp

Verify the connection registered. Open Claude Code and run: /mcp

agent-handler should appear under Local MCPs with a connected status.

Related: A guide to integrating a Google Slides MCP with Claude Code

4. Authenticate Gamma

Open a Claude Code session and test it with: "List my recent Gamma decks and summarize the title and slide count of each one created in the last 30 days."

The first time you use a Gamma tool, a Magic Link will appear to authenticate the connector.

Once authenticated, you should see an output like the following:

{{this-blog-only-cta}}

Gamma MCP FAQ

In case you have more questions on setting up and using the Gamma MCP in Claude Code, we've addressed several more commonly-asked questions below.

What can you do once the Gamma MCP is connected to Claude Code?

With Gamma connected, Claude Code can:

• Create decks: generate a new Gamma presentation from structured content, such as a changelog, sprint summary, or architecture doc, without opening a browser

• List decks: browse existing presentations in your Gamma workspace to find the right deck before querying or updating it

• Read deck content: retrieve the content and structure of an existing presentation so an agent can summarize, extend, or cross-reference it

• Update decks: modify an existing deck with new content when source data changes, such as appending a new slide when a new incident closes

• Cross-reference content: combine Gamma deck data with other connected tools, such as pulling this week's closed GitHub issues and generating a release summary deck from them

Why use Merge Agent Handler vs. a self-hosted Gamma MCP server?

You can build a self-hosted MCP server that calls the Gamma API directly. For a solo developer generating decks from their own workspace, the setup is straightforward: get an API key, write tool schemas for the operations you need, and wire it to Claude Code.

The problems emerge when multiple people need access or when the decks contain sensitive content.

A self-hosted setup gives your agent credentials that carry access to everything in the workspace, not just the specific decks you intend to expose. There are no tool-level controls to limit an agent to read-only access or prevent it from creating decks outside the intended scope.

At team scale, credential management adds overhead. Each developer either shares API credentials (a security risk) or manages their own configuration (a maintenance burden). There is no central log of which agent created or modified which deck, and no clean way to revoke one agent's access without rotating credentials for everyone.

Merge Agent Handler adds a control layer at the tool level.

You define exactly which Gamma tools each Tool Pack exposes, so a read-only summarization agent never gets access to deck creation or deletion tools. And each Registered User has isolated credentials and a separate audit trail.

Why connect Gamma to Claude Code?

Gamma is where a lot of internal communication gets finalized: product updates, technical proposals, launch readouts, engineering retrospectives. The content for all of those already exists in code, tickets, and logs. The gap is moving it from the terminal into a shareable deck, which currently requires a browser and manual formatting.

Connecting Gamma via MCP closes that gap.

A developer can ask Claude Code to pull the last sprint's closed Jira tickets, group them by theme, and create a Gamma retrospective deck with one slide per theme; a release manager can ask Claude Code to read the changelog since the last tag, identify breaking changes, and generate a structured deck for the API consumers call, and the list of examples goes on.