Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Random Persona MCP Server inject a friendly persona for this conversation"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP (Model Context Protocol) server exposing the six-layer persona engine.
pip install fastmcp
python server.py
# → MCP server on http://127.0.0.1:4568Related MCP server: Persona MCP
Tool | Description |
| Get system-prompt injection for current session state |
| Post-process LLM response (silence, filler) |
| Get human-readable state display |
| Handle /persona commands |
Configure astrbot_plugin_random_persona to point at this server:
{
"mcp_url": "http://127.0.0.1:4568"
}Variable | Default | Description |
|
| Server port |
|
| Bind address |
|
| State persistence directory |
|
| Transport: |
AstrBot plugin ──MCP──► persona_inject(session_id, user_id, message)
persona_post_process(session_id, response)
persona_command(...)
Internal pipeline:
Mood drift → Appraisal → Emotion decay → Relationship → SpeechAct → Lexicon → PromptMIT
This server cannot be deployed
Persistent AI entity framework with causal memory, emotional state, and identity.
Memory for deep conversational context across any platform
Universal persistent memory and knowledge retrieval layer for AI agents and LLMs.
AI routing, memory, guardrails, and governance. Routes across Claude, GPT, Gemini.