Google Slides MCP

🚀 Google Slides MCP Server

Google Slides MCP Server is a tool that interacts with the Google Slides API using the Model Context Protocol. It enables communication via standard input/output, allowing users to create, read, and modify Google Slides presentations.

🚀 Quick Start

✨ Features

• Communicate with the Google Slides API using the Model Context Protocol.
• Create, read, and modify Google Slides presentations via standard input/output.

📦 Installation

To run the Google Slides MCP Server, ensure the following prerequisites are met:

• Install Node.js (version 14 or higher is recommended).
• Install the npm package management tool.
• Configure a valid Google Cloud project to obtain API access.
• Obtain OAuth 2.0 credentials, including the client ID, client secret, and refresh token.

💻 Usage Examples

Basic Usage

After compiling the code, run the following command to start the server:

npm run start

Upon successful startup, the following message will be displayed: Google Slides MCP Server has started and is connected via standard input/output.

📚 Documentation

Available Tools

1. Create a Presentation

Create a new Google Slides presentation.

Input:

• title (string, required): The title of the new presentation.

Output: Returns a JSON object containing detailed information about the new presentation.

2. Get a Presentation

Retrieve detailed information about an existing presentation.

Input:

• presentationId (string, required): The ID of the presentation to retrieve.
• fields (string, optional): Specify the data fields to return (e.g., "slides,pageSize").

Output: Returns a JSON object containing detailed information about the presentation.

3. Batch Update a Presentation

Apply a series of update operations to a presentation. This is the primary method for modifying slides.

Input:

• presentationId (string, required): The ID of the presentation to update.
• requests (array, required): An array of objects containing update requests. Refer to the Google Slides API's batchUpdate documentation for the specific structure.
• writeControl (object, optional): Control the execution of write requests (e.g., using a revision ID).

Output: Returns a JSON object containing the results of the batch update.

4. Get a Page

Retrieve detailed information about a specific page in a presentation.

Input:

• presentationId (string, required): The ID of the presentation containing the page to retrieve.
• pageObjectId (string, required): The ID of the page (slide) object to retrieve.

Output: Returns a JSON object containing detailed information about the page.

5. Summarize a Presentation

Extract and format all text content from a presentation for easy summarization.

Input:

• presentationId (string, required): The ID of the presentation to summarize.
• include_notes (boolean, optional): Whether to include speaker notes, default is false.

Output: Returns a JSON object containing the following information:

• title: The title of the presentation.
• slideCount: The total number of slides.
• lastModified: Revision information.
• slides: An array of slides containing the following:
  • slideNumber: The position in the presentation.
  • slideId: The ID of the slide object.
  • content: All text extracted from the slide.
  • notes: Speaker notes (if requested and available).

(More tools can be added by extending src/index.ts)