MCP ExplorerExplorer

Mcp Server Python

@punkpeyeon 16 days ago
1 MIT
FreeCommunity
AI Systems
A MCP server for Cappt (Python version)

Overview

What is Mcp Server Python

mcp-server-python is a Model Context Protocol server designed for generating outlines and presentations using Cappt. It allows users to create structured presentations from standard outlines.

Use cases

Use cases include generating lecture outlines for educational purposes, creating business presentation slides from articles, and developing visual content for workshops.

How to use

To use mcp-server-python, install it using the ‘uv’ tool, create a virtual environment, activate it, and run the server with your Cappt token. You can generate outlines and presentations by calling the respective functions.

Key features

Key features include the ability to generate standard outlines from user input and create presentations from those outlines. It also provides options to include galleries in presentations and offers debugging tools.

Where to use

mcp-server-python can be used in educational settings, business presentations, and any scenario where structured presentation generation is needed.

Content

mcp-server-cappt: A MCP server for Cappt

Cappt

Overview

A Model Context Protocol server for generating outline and presentation with cappt.cc.

Tools

  1. generate_presentation
  • Generate a presentation from outline (generated by generate_outline)
  • Input:
    • outline (string): a standard outline
    • include_gallery (bool): whether to include gallery in result
  • Returns:
    • record_id: the record ID of the generated presentation
    • status: the status of the generation process’
    • total_page: the total number of slides in the presentation
    • editor_url: the URL to edit the presentation
    • title: the title of the presentation
    • thumbanil: the thumbnail of the presentation
      • gallery: the gallery of the presentation

Prompts

  1. geenrate_outline
  • Generate a standard outline
  • Input:
    • input (string): user input, eg, title, article, etc.
  • Returns: A standard outline

Installation

Using uv (recommended)

When using uv no specific installation is needed.

cd path/to/repo
# Create a virtual environment
uv venv
# Linux or macOS
source venv/bin/activate
# Windows
venv\Scripts\activate
# Install the package
uv install -e .
# Run the server
uv run mcp-server-cappt --cappt-token YOUR_CAPPT_TOKEN

Configuration

Usage with Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "sentry": {
      "command": "uv",
      "args": [
        "--directory",
        "path/to/repo",
        "run",
        "mcp-server-cappt"
      ],
      "env": {
        "CAPPT_TOKEN": "YOUR_CAPPT_TOKEN"
      }
    }
  }
}

Debugging

You can use the MCP inspector to debug the server. Please make sure you have installed this package with uv, then run:

npx @modelcontextprotocol/inspector uv run mcp-server-cappt --cappt-token YOUR_CAPPT_TOKEN

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

Tools

No tools

Comments