mcpField
C
codevideo-mcp

codevideo-mcp

Local
github.com/codevideoMedia & Design2Updated 70w ago
Repository

About codevideo-mcp

codevideo-mcp lets software educators create and transform lessons and related content using natural-language requests. It supports formats including video, blog posts, and HTML, as well as validation and translation of CodeVideo actions.

Key features

  1. 01Generate software lessons from prompts
  2. 02Convert actions to video, blogs, or HTML
  3. 03Translate lessons
  4. 04Validate CodeVideo JSON actions

Use cases

  1. 01Create a React useState video lesson
  2. 02Turn lesson actions into a blog post
  3. 03Translate a lesson into Spanish

MCP support

The MCP server exposes CodeVideo content creation, conversion, translation, and validation capabilities to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "codevideo": {
      "command": "npx",
      "args": [
        "-y",
        "@fullstackcraftllc/codevideo-mcp"
      ]
    }
  }
}
Run commandnpx -y @fullstackcraftllc/codevideo-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@fullstackcraftllc/codevideo-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

codevideo-mcp

The MCP server for CodeVideo.

Create software educational content using natural language.

Examples:

Creation:

  • "Build a video lesson on how to use the useState hook in React"
  • "Can you create a video lesson compare and contrasting how to program concurrently in C#, Go, and Rust?"
  • Can you give me a markdown blog post on how to use the useState hook in React?"

Conversion:

  • "Please convert these CodeVideo JSON actions to a video"
  • "Convert these CodeVideo JSON actions to a blog post"
  • "Convert these CodeVideo JSON actions to HTML"
  • "Can you convert this English-based lesson to Spanish?"

Validation:

  • "Are these CodeVideo JSON actions valid?"

Usage with Claude Desktop

Simply drop the following into your claude_desktop_config.json file:

{
    // ... other MCP servers
    "codevideo-mcp": {
        "command": "npx",
        "args": [
            "-y",
            "@fullstackcraftllc/codevideo-mcp@latest"
        ],
        "env": {
            "ELEVENLABS_API_KEY": "your-elevenlabs-api-key",
            "ELEVENLABS_VOICE_ID": "your-elevenlabs-voice-id",
            "PATH_TO_CODEVIDEO_CLI": "/path/to/your/codevideo-cli/binary",
        }
    },
    // ... other MCP servers
}

Be sure to restart Claude after modifying this config!

After restarting Claude Desktop, if installation was successful, you should see codevideo-mcp in the list of installed MCPs:

codevideo-mnp successfully installed in Claude Desktop

Local Development

Clone this repository:

git clone https://github.com/codevideo/codevideo-mcp.git

Then, install the dependencies and build the project:

cd codevideo-mcp
npm install
npm run build

Then, use the following JSON to run the local version on your Claude Desktop:

    // ... other MCP servers
    "codevideo-mcp": {
        "command": "npx",
        "args": [
            "tsx",
            "/path/to/your/clone/of/codevideo-mcp/src/index.ts"
        ],
        "env": {
            "ELEVENLABS_API_KEY": "your-elevenlabs-api-key",
            "ELEVENLABS_VOICE_ID": "your-elevenlabs-voice-id",
            "PATH_TO_CODEVIDEO_CLI": "/path/to/your/codevideo-cli/binary",
        }
    }
    // ... other MCP servers

Known Issues

  • Currently, creating entire courses seems to be a bit flakey and perhaps too large for the context window for Claude. We're working on refining the full course flow. Single lesson, or action array generation both seem to work well.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.