OriginalVoices

You can run the OriginalVoices MCP Server to access AI twins designed for audience research. This server lets you connect with OriginalVoices data sources through a local or remote client, enabling interactive questions and insights from specific audiences.

How to use

You interact with the MCP server through an MCP client configured to communicate with the server. Start the server using either the local runtime option or an executable, then point your client to the server endpoint you configured. Use the server to pose questions to your target audience or fetch contextual responses from OriginalVoices AI twins, enabling streamlined audience research workflows.

How to install

Prerequisites you need before installation: a supported Node.js runtime environment (Node.js 14+ is commonly used for MCP servers) and npm (Node package manager). Ensure you have internet access to install dependencies.

Install the MCP server package using npm.

npm install @originalvoices/mcp-server

Configuration and usage tips

Configure access to the OriginalVoices API by providing your API key in the environment. You can run the server in different ways depending on your integration setup.

Example configuration blocks you can adapt when adding the server to your client setup.

{
  "mcpServers": {
    "originalvoices": {
      "command": "npx",
      "args": ["@originalvoices/mcp-server"],
      "env": {
        "ORIGINALVOICES_API_KEY": "your-api-key"
      }
    }
  }
}

{
  "mcpServers": {
    "originalvoices": {
      "command": "node",
      "args": ["/path/to/ov-mcp-server/dist/index.js"],
      "env": {
        "ORIGINALVOICES_API_KEY": "your-api-key"
      }
    }
  }
}

Examples of available tools and actions

The server provides a tool to ask questions to OriginalVoices AI twins. You can specify the audience and the questions you want to ask, then collect responses for analysis.

Example tool usage configuration you can adapt in your MCP client.

{
  "name": "ask_twins",
  "audience": "UK, 18-30, fitness enthusiasts",
  "questions": [
    "When purchasing running shoes, what's most important to you?",
    "How often do you replace your running shoes?"
  ]
}

Development

To contribute or run a local development environment, install dependencies, build, and run in watch mode.

# Install dependencies
npm install

# Build
npm run build

# Watch mode
npm run dev