Office PowerPoint MCP server for AI agents

This MCP server enables PowerPoint manipulation through the Model Context Protocol, providing tools for creating, editing, and manipulating presentations programmatically. It uses python-pptx to interact with PowerPoint files and is designed to be integrated with AI tools like Claude.

Installation

Installing via Smithery

To install the PowerPoint Manipulation Server automatically via Smithery:

npx -y @smithery/cli install @GongRzhe/Office-PowerPoint-MCP-Server --client claude

Prerequisites

Python 3.10 or higher
pip package manager

Installation Options

Option 1: Using the Setup Script (Recommended)

The easiest way to set up the PowerPoint MCP Server is using the provided setup script:

python setup_mcp.py

This script will:

Check prerequisites
Offer installation options (PyPI or local development)
Install required dependencies
Generate the appropriate MCP configuration file
Provide instructions for Claude Desktop integration

Option 2: Manual Installation

Clone the repository:

git clone https://github.com/GongRzhe/Office-PowerPoint-MCP-Server.git
cd Office-PowerPoint-MCP-Server

Install dependencies:
```
pip install -r requirements.txt
```
Make the server executable:
```
chmod +x ppt_mcp_server.py
```

Usage

Starting the Server

Run the server:

python ppt_mcp_server.py

MCP Configuration

Option 1: Local Python Server

Add the server to your MCP settings configuration file:

{
  "mcpServers": {
    "ppt": {
      "command": "python",
      "args": ["/path/to/ppt_mcp_server.py"],
      "env": {}
    }
  }
}

Option 2: Using UVX (No Local Installation Required)

If you have uvx installed:

{
  "mcpServers": {
    "ppt": {
      "command": "uvx",
      "args": [
        "--from", "office-powerpoint-mcp-server", "ppt_mcp_server"
      ],
      "env": {}
    }
  }
}

Available Tools

Presentation Tools

create_presentation: Create a new PowerPoint presentation
open_presentation: Open an existing PowerPoint presentation from a file
save_presentation: Save the current presentation to a file
get_presentation_info: Get information about the current presentation
set_core_properties: Set core document properties of the current presentation

Slide Tools

add_slide: Add a new slide to the current presentation
get_slide_info: Get information about a specific slide
populate_placeholder: Populate a placeholder with text
add_bullet_points: Add bullet points to a placeholder

Text Tools

add_textbox: Add a textbox to a slide

Image Tools

add_image: Add an image to a slide
add_image_from_base64: Add an image from a base64 encoded string to a slide

Table Tools

add_table: Add a table to a slide
format_table_cell: Format a table cell

Shape Tools

add_shape: Add an auto shape to a slide

Chart Tools

add_chart: Add a chart to a slide

Examples

Creating a New Presentation

# Create a new presentation
result = use_mcp_tool(
    server_name="ppt",
    tool_name="create_presentation",
    arguments={}
)
presentation_id = result["presentation_id"]

# Add a title slide
result = use_mcp_tool(
    server_name="ppt",
    tool_name="add_slide",
    arguments={
        "layout_index": 0,  # Title slide layout
        "title": "My Presentation",
        "presentation_id": presentation_id
    }
)
slide_index = result["slide_index"]

# Populate subtitle placeholder
result = use_mcp_tool(
    server_name="ppt",
    tool_name="populate_placeholder",
    arguments={
        "slide_index": slide_index,
        "placeholder_idx": 1,  # Subtitle placeholder
        "text": "Created with PowerPoint MCP Server",
        "presentation_id": presentation_id
    }
)

# Save the presentation
result = use_mcp_tool(
    server_name="ppt",
    tool_name="save_presentation",
    arguments={
        "file_path": "my_presentation.pptx",
        "presentation_id": presentation_id
    }
)

Adding a Chart

# Add a chart slide
result = use_mcp_tool(
    server_name="ppt",
    tool_name="add_slide",
    arguments={
        "layout_index": 1,  # Content slide layout
        "title": "Sales Data",
        "presentation_id": presentation_id
    }
)
slide_index = result["slide_index"]

# Add a column chart
result = use_mcp_tool(
    server_name="ppt",
    tool_name="add_chart",
    arguments={
        "slide_index": slide_index,
        "chart_type": "column",
        "left": 1.0,
        "top": 2.0,
        "width": 8.0,
        "height": 4.5,
        "categories": ["Q1", "Q2", "Q3", "Q4"],
        "series_names": ["2023", "2024"],
        "series_values": [
            [100, 120, 140, 160],
            [110, 130, 150, 170]
        ],
        "has_legend": True,
        "legend_position": "bottom",
        "has_data_labels": True,
        "title": "Quarterly Sales",
        "presentation_id": presentation_id
    }
)

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.