LLMMO Game Server
Enables LLM-driven text game state management by exposing MCP tools for managing players, locations, items, entities, and abstract concepts.
README
LLMMO Game Server
MCP server for LLM-driven text game state management. Exposes tools for managing players, locations, items, entities, and abstract concepts via the MCP protocol.
Built with FastAPI, FastMCP, Python 3.14.
Setup
Docker (recommended)
cp .env.example .env # adjust if needed
docker compose up --build app
Local
uv sync
uvicorn llmmo.main:app --reload --host 0.0.0.0 --port 8111
Configuration
Environment variables (.env):
| Variable | Default | Description |
|---|---|---|
BACKEND__RUN__HOST |
localhost |
Server host |
BACKEND__RUN__PORT |
8111 |
Server port |
BACKEND__DB__BASE_PATH |
.state |
Game state storage directory |
BACKEND__CORS__ORIGINS |
["http://localhost:8111"] |
Allowed CORS origins |
BACKEND__CORS__CREDENTIALS |
true |
Allow credentials |
BACKEND__CORS__METHODS |
["*"] |
Allowed HTTP methods |
BACKEND__CORS__HEADERS |
["*"] |
Allowed headers |
Authentication
- Register at
GET /registerorPOST /register - Get an API key via
POST /auth/api-keys(JSON:{"username": "...", "password": "..."}) - Use the key as a Bearer token for MCP endpoints:
Authorization: Bearer <api_key>
Each user gets isolated game state stored in .state/<username_hash>/.
MCP Endpoint
MCP server is mounted at /mcp. Connect your MCP client to http://localhost:8111/mcp.
Data Model
- Player — name, inventory (
item_id -> quantity), current location - Location — name, description
- Item — name, description (global, referenced by players)
- Entity — name, description, optional location (NPCs, objects, monsters)
- Abstract — name, description (events, topics, lore — not tied to locations)
All IDs are UUIDs. State is persisted as JSON files per user.
Development
uv sync --all-groups # install dev deps
Before commit: ruff (lint/format), mypy (type check).
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.