Godot MCP Server For Local LLM
БесплатноНе проверенA sleek C# class library designed to integrate a local Model Context Protocol (MCP) server with a local Large Language Model (LLM), tailored for Godot-based gam
Описание
A sleek C# class library designed to integrate a local Model Context Protocol (MCP) server with a local Large Language Model (LLM), tailored for Godot-based games. This library empowers your LLM to seamlessly interact with the game world through structured tool commands, bringing your Echoes of Ir-style vision to life.
README
A sleek C# class library designed to integrate a local Model Context Protocol (MCP) server with a local Large Language Model (LLM), tailored for Godot-based games. This library empowers your LLM to seamlessly interact with the game world through structured tool commands, bringing your Echoes of Ir-style vision to life.
Features
- MCPHandler: Masterfully routes tool commands from the LLM (e.g., opening doors or disarming traps) to your game logic with precision.
- LLMManager: Seamlessly sends prompts to a local LLM server and processes responses, including tool command execution.
- Extensible Actions: Effortlessly register new in-game actions for the LLM to wield, expanding your creative control.
- Godot Integration: Crafted as a Godot Node, with practical examples leveraging Godot's
printand node systems for a native feel.
Getting Started
Requirements
- .NET 9.0: Ensure your development environment is up to date.
- Godot: Required for seamless integration (tested with Godot 4.4).
- Local LLM Server: Must support a
/completionendpoint with JSON input/output (e.g., llama.cpp or Ollama with Mistral Nemo).
Installation
- Clone the Repository: Grab the latest code with
git clone [repository-url]. - Integrate the Project: Add the project to your solution or reference the compiled DLL in your Godot C# project.
Usage
- Add MCPHandler: Instantiate
MCPHandleras a node in your Godot scene. - Query the LLM: Use
LLMManager.QueryLLM(prompt, port)to send prompts to your local LLM server. - Provide Environment Context: Include the character’s surroundings with your input, e.g.,
E:door_456,S:empty,W:trap_987,N:empty, to guide the LLM’s decisions. - Handle LLM Responses: The LLM may return tool commands in JSON format, such as: { "action": "open_door", "parameters": { "target": "door_1" } } 5.Route Commands: MCPHandler directs these commands to your registered handler methods for execution.
Example System Prompt
Enhance your LLM’s capabilities by adding this to its system prompt:
You can use tools to interact with the game world. Available tools: open_door: Description: Opens a closed door in the game. Parameters: target (string): The identifier or path of the door to open. Example usage: {""action"":""open_door"",""parameters"": {""target"": ""door_1""}}
disarm_trap: Description: Attempts to disarm a trap in the game. Parameters: target (string): The identifier or path of the trap to disarm. Example usage: {""action"": ""disarm_trap"",""parameters"": {""target"": ""trap_3""}} When you want to perform an in-game action, respond with a JSON object using the exact format in example usage. Only use the defined actions and parameters. Also comment on the action.`
Extending the Library
Unlock new possibilities by registering custom actions: MCPHandler.Instance.RegisterAction("your_action", YourHandlerMethod);
License
This project is released under the MIT License. Feel free to use, modify, and distribute it, but please include the original copyright and license notice. See LICENSE for details.
Acknowledgements
Inspired by the retro grit of Eye of the Beholder and powered by the indie spirit of Echoes of Ir. Thanks to the Godot and LocalLLaMA communities for the support!
Contact
Have questions or ideas? Reach out to [email protected] for support or collaboration.
Установка Godot MCP Server For Local LLM
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/viktorfaubl/Godot-MCP-server-for-local-LLMFAQ
Godot MCP Server For Local LLM MCP бесплатный?
Да, Godot MCP Server For Local LLM MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Godot MCP Server For Local LLM?
Нет, Godot MCP Server For Local LLM работает без API-ключей и переменных окружения.
Godot MCP Server For Local LLM — hosted или self-hosted?
Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.
Как установить Godot MCP Server For Local LLM в Claude Desktop, Claude Code или Cursor?
Открой Godot MCP Server For Local LLM на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
автор: lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
MCPHub
Website to list high quality MCP servers and reviews by real users. Also provide online chatbot for popular LLM models with MCP server support.
MCP Servers Rating and User Reviews
Website to rate MCP servers, write authentic user reviews, and [search engine for agent & mcp](http://www.deepnlp.org/search/agent)
mkinf
An Open Source registry of hosted MCP Servers to accelerate AI agent workflows.
Compare Godot MCP Server For Local LLM with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
