PowerPoint Creator MCP Server
A mcp server supporting you to generate powerpoint using LLM and natural language automatically.
ltc6539
README
PowerPoint Creator MCP Server
This MCP server enables dynamic creation and modification of PowerPoint presentations via a set of API tools. Built on top of MCP and using the python-pptx library, this server provides a flexible interface to add slides, images, tables, and more.
Features
-
Create Presentations
Initialize a new PowerPoint presentation using a title that generates a unique presentation ID. -
Slide Operations
- Title Slide: Add a title slide with an optional subtitle.
- Content Slide: Create slides with a title and bullet-point content.
- Section Slide: Insert a section divider slide with a large centered title and an optional background color.
- Image Slide: Add slides featuring images from local files or URLs with titles and descriptive alt text.
- Table Slide: Insert slides containing tables with defined headers and row data.
-
Presentation Management
- Save Presentation: Write the presentation to a specified file path, handling temporary directories if needed.
- Download Link: Generate a data URI with base64-encoded presentation content for direct download.
- Presentation Info: Retrieve metadata about the presentation such as the number of slides and available slide layouts.
- Presentation Outline: Obtain a text-based outline of the presentation structure via a dedicated resource endpoint.
- Remove Slide: Delete a slide by its 1-based index.
- Export to Base64: Export the complete presentation as a base64-encoded string for further processing.
Installation
-
Clone the Repository
git clone https://github.com/ltc6539/mcp-ppt.git cd mcp-ppt
-
Create a Virtual Environment (Optional but Recommended)
python3 -m venv venv source venv/bin/activate # On Windows use: venv\Scripts\activate
-
Install Dependencies
pip install -r requirements.txt
Usage with Claude Desktop
Add this to your claude_desktop_config.json
:
{
"mcpServers": {
"PowerPoint Creator": {
"command": "uv",
"args": [
"run",
"--with",
"mcp[cli]",
"--with",
"python-pptx",
"mcp",
"run",
"your_path/mcp-ppt/main.py"
]
}
}
}
Be sure to modify your_path
into the real path
You may need to put the full path to the uv executable in the command field. You can get this by running which uv
on MacOS/Linux or where uv
on Windows.
During startup, the server logs Python and python-pptx version information to stderr. Any errors during execution are also printed to stderr for easy debugging.
API Endpoints / Tools
Each MCP tool function is directly accessible via the MCP server. Below are the primary operations available:
1. Create Presentation
- Function:
create_presentation(title: str) -> str
- Description: Initializes a new presentation and returns a unique presentation ID.
2. Add Title Slide
- Function:
add_title_slide(prs_id: str, title: str, subtitle: Optional[str] = None) -> str
- Description: Adds a title slide to the specified presentation.
3. Add Content Slide
- Function:
add_content_slide(prs_id: str, title: str, content: List[str]) -> str
- Description: Inserts a content slide with a title and multiple bullet points.
4. Add Section Slide
- Function:
add_section_slide(prs_id: str, section_title: str, background_color: Optional[str] = None) -> str
- Description: Creates a section divider slide with a customizable background color and large, centered text.
5. Add Image Slide
- Function:
add_image_slide(prs_id: str, title: str, image_path: str, image_description: str) -> str
- Description: Adds an image slide. The image can be loaded from a local file or downloaded from a URL.
6. Add Table Slide
- Function:
add_table_slide(prs_id: str, title: str, headers: List[str], rows: List[List[str]]) -> str
- Description: Inserts a slide containing a table defined by column headers and rows of data.
7. Save Presentation
- Function:
save_presentation(prs_id: str, output_path: str) -> str
- Description: Saves the presentation to the specified output path, managing temporary directories if necessary.
8. Get Presentation Download Link
- Function:
get_presentation_download_link(prs_id: str) -> str
- Description: Returns a data URI with base64-encoded presentation data for direct browser download.
9. Get Presentation Info
- Function:
get_presentation_info(prs_id: str) -> str
- Description: Retrieves metadata such as slide count and details on available slide layouts.
10. Get Presentation Outline
- Resource Endpoint:
presentation://{prs_id}/outline
- Description: Provides a text representation of the presentation structure, including slide titles and content summaries.
11. Remove Slide
- Function:
remove_slide(prs_id: str, slide_index: int) -> str
- Description: Removes a slide identified by its 1-based index from the presentation.
12. Export to Base64
- Function:
export_to_base64(prs_id: str) -> str
- Description: Exports the presentation as a base64-encoded string (with the first 100 characters shown as a sample).
Error Handling & Debugging
-
Error Checks:
Each tool validates input (e.g., verifying presentation IDs or file existence) and returns descriptive error messages. -
Temporary Directories:
The server ensures that files are saved in writable directories (typically/tmp
) and falls back accordingly if a provided path is read-only. -
Logging:
Errors and version information are output to stderr to aid in debugging and monitoring.
Contributing
Contributions are welcome. If you encounter issues or have suggestions for improvements, please open an issue or submit a pull request.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.