Connects to OriginalVoices, a platform that uses AI twins to simulate audience responses for market research. Exposes a single tool, ask_twins, where you pass an audience description like "UK, 18-30, fitness enthusiasts" and an array of questions. It returns simulated responses from AI models trained to represent that demographic. Useful when you need quick audience insights without running actual surveys, or want to test messaging and product concepts across different market segments. Requires an API key from the OriginalVoices platform. The audience parameter takes freeform text descriptions, so you can target pretty much any demographic combination you need to understand.
An MCP (Model Context Protocol) server that provides access to OriginalVoices AI twins for audience research.
npm install @originalvoices/mcp-server
| Variable | Description | Required |
|---|---|---|
ORIGINALVOICES_API_KEY | Your OriginalVoices API key | Yes |
Add to your claude_desktop_config.json:
{
"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"
}
}
}
}
Ask questions to a specific audience using OriginalVoices AI twins.
Parameters:
| Name | Type | Description |
|---|---|---|
audience | string | Description of the audience |
questions | string[] | Array of questions to ask the audience |
Example:
{
"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?"
]
}
# Install dependencies
npm install
# Build
npm run build
# Watch mode
npm run dev
You can create an API key on the OriginalVoices Platform.
MIT