mcp-server-cappt: A MCP server for Cappt

@cappt-team

Repository Homepage

Basic information

About mcp-server-cappt: A MCP server for Cappt

A MCP server for Cappt

#mathgpt #math-solver #math-assistant

mcp-server-cappt: A MCP server for Cappt config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "sentry": {
      "command": "node",
      "args": [
        "path/to/repo/dist/index.js"
      ],
      "env": {
        "CAPPT_TOKEN": "YOUR_CAPPT_TOKEN"
      }
    }
  }
}

mcp-server-cappt: A MCP server for Cappt tools

`outline` (string): a standard outline

`record_id`: the record ID of the generated presentation

Overview

What is mcp-server-cappt?

A Model Context Protocol server for generating outlines and presentations with cappt.cc. It allows AI agents to create presentation content and editable links programmatically.

How to use mcp-server-cappt?

Install by cloning the repo and running npm install && npm run build. For Claude Desktop, add an entry to claude_desktop_config.json with command node path/to/dist/index.js and the environment variable CAPPT_TOKEN set to your Cappt API token.

Key features of mcp-server-cappt

Generate a presentation from an existing outline.
Generate a standard outline from user input (title, article, etc.).
Optionally include a gallery and preview in results.
Returns an editor URL, thumbnail, and slide count.
Easily integrates with Claude Desktop.
Licensed under the MIT License.

Use cases of mcp-server-cappt

Automatically produce a presentation outline from a topic.
Create an editable presentation link from a few sentences.
Generate a presentation from a structured outline.
Add presentation generation capabilities to MCP‑enabled assistants.

Frequently asked questions

What is the purpose of mcp-server-cappt?

It provides MCP tools to generate outlines and presentations with the cappt.cc platform.

What tools are available?

Two tools: `generate_outline` prompt (accepts a string input and returns a standard outline) and `generate_presentation` tool (takes an outline and optional booleans for gallery/preview, then returns presentation details).

What environment variable is required?

The `CAPPT_TOKEN` environment variable must be set to your Cappt API token.

How can I debug the server?

Use the MCP inspector: `npx @modelcontextprotocol/inspector node dist/index.js`.

What license does this server use?

It is licensed under the MIT License.

Comments

More Other MCP servers

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

YOUB

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

PickFu MCP

PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct

Screenpipe

screenpipe

YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

22.0K

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K