Interview Roleplay

by ejb503

5 stars
3.2k downloads
Not rated
GitHub

About

Provides an AI-powered interview roleplay system for dynamic simulation of customizable interview scenarios, enabling practice and skill improvement for job seekers.

Details

Author
ejb503
Repository
Ejb503/systemprompt-mcp-interview
GitHub stars
5
Downloads
3,206
License
Other
Categories
Design, Developer Tools, AI, Database, Infrastructure, Frontend, Other
Tags
#mobile

- Interview Roleplay

- Practice interviews with AI-powered personas
- Receive real-time feedback on responses
- Customizable interview scenarios
- Natural conversation flow

- AI Integration

- Advanced natural language processing
- Context-aware responses
- Real-time voice synthesis
- Streaming responses for immediate feedback

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Interview Roleplay
    Command (node, npx, python, etc.) npx
    Arguments
    • Argument 1 -y
    • Argument 2 @highlight/mcp-server

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

1/ Connect the MCP server in your systemprompt.io console
2/ Add a CV in text format to the summarize_cv tool
3/ List CVs and copy the uri of the resource
4/ Configure interview using configure_interview tool and resource uri with your instructions
5/ Activate the agent, and your roleplay will be available

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "interview roleplay": {
            "env": {},
            "args": [
                "-y",
                "@highlight/mcp-server"
            ],
            "command": "npx"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Macos

{
    "env": [],
    "args": [
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "npx"
}

Windows

{
    "env": [],
    "args": [
        "/c",
        "npx",
        "-y",
        "@highlight/mcp-server"
    ],
    "command": "cmd"
}

systemprompt-mcp-interview

npm version
License: Apache-2.0
Twitter Follow
Discord

Website| Get API Key

A specialized Model Context Protocol (MCP) server that enables AI-powered interview roleplay scenarios.

This server is designed to work with the systemprompt-io system, providing an interactive voice interface for interview practice.

API key required. (currently free)

Features

- Interview Roleplay

- Practice interviews with AI-powered personas
- Receive real-time feedback on responses
- Customizable interview scenarios
- Natural conversation flow

- AI Integration

- Advanced natural language processing
- Context-aware responses
- Real-time voice synthesis
- Streaming responses for immediate feedback

Installation

1/ Connect the MCP server in your systemprompt.io console
2/ Add a CV in text format to the summarize_cv tool
3/ List CVs and copy the uri of the resource
4/ Configure interview using configure_interview tool and resource uri with your instructions
5/ Activate the agent, and your roleplay will be available

Demo

Watch our demonstration video of an AI-powered interview roleplay scenario where a candidate interviews for the position of "King of the Gorillas":

▶️ Watch Demo Video
▶️ Watch Setup Video

The demo showcases:

- Natural conversation flow with AI interviewer
- Creative scenario-based questions
- Real-time response handling
- Dynamic interview progression
- Personality assessment through roleplay

Documentation

- Full API Documentation
- Client Setup Guide
- Server Configuration

Development

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.