Persona Sessions

Provides a framework for loading persona profiles, managing timer-based sessions, and delivering guided, structured conversations with adaptive flows and feedback.

python

5

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mattjoyce-mcp-persona-sessions": {
      "command": "/path/to/venv/python",
      "args": [
        "/path/to/mcp-persona-sessions/mcp-persona-sessions.py"
      ]
    }
  }
}

You can run a persona-driven session management server that guides AI interactions through interview prep, personal reflection, and coaching. This MCP server lets you load detailed persona profiles, manage session flow with timers, and receive structured feedback, all in a secure, adaptable framework for meaningful conversations.

How to use

Begin a session by selecting a persona and a session framework, then start the session timer to track duration. You can load tailored personas for realistic role-play, such as an interviewer, board member, or reflective companion, and rely on predefined session templates to align goals and outcomes. As the conversation unfolds, the system adapts to new developments and provides post-session feedback on performance and communication.

How to install

Prerequisites: You need Python 3.8 or newer and an MCP-compatible AI assistant (for example Claude Desktop). Ensure you have a working Python environment and that your MCP client can reach local stdio-based servers.

# 1) Clone the project
git clone https://github.com/mattjoyce/mcp-persona-sessions.git
cd mcp-persona-sessions

# 2) Install dependencies
pip install fastmcp

# 3) Set up configuration (copy and edit as needed)
cp config.yaml.example config.yaml
# Edit config.yaml with your preferences

Additional configuration and usage notes

Configure the MCP client to connect to the local server. Use the provided client configuration sample to point the client to the local runtime and script.

{
  "mcpServers": {
    "persona_sessions": {
      "command": "/path/to/venv/python",
      "args": ["/path/to/mcp-persona-sessions/mcp-persona-sessions.py"],
      "cwd": "/path/to/mcp-persona-sessions"
    }
  }
}

Configuration

The server uses a configuration file to locate persona definitions and session templates. You can customize the personas and session types to fit your needs.

Example settings include the path to persona definitions, the session types file, and fallback persona definitions.

Available tools

list_session_frameworks

Browse available session types and templates to choose a suitable structure for your conversation.

list_session_personas

View all available personas that you can load into a session.

get_persona_details

Retrieve full details of a specific persona, including identity, communication style, and expertise areas.

assess_session_readiness

Check if the system is ready to start a session, including persona availability and framework readiness.

initialize_session

Begin a structured session with a selected persona and template.

start_timer

Start a session timer with an optional duration to track time spent.

check_timer_status

Monitor the running timer to see elapsed time and remaining duration.

stop_timer

End the timer and conclude the current session.

get_session_feedback

Analyze the session transcript and provide detailed feedback on performance and communication.