React Native Godot Documentation MCP Server

React Native Godot Documentation MCP Server

Enables intelligent access to React Native Godot documentation, examples, API references, and troubleshooting guides through searchable tools optimized for LLM workflows.

Category
访问服务器

README

React Native Godot Documentation MCP Server

A powerful Model Context Protocol (MCP) server for intelligent access to React Native Godot documentation, examples, and implementation guides. This server enables LLMs to efficiently fetch and search documentation from the react-native-godot repository by Born.com and Migeran.

🚀 Features

Agent-Centric Design

This MCP server follows best practices for agent-oriented tool design:

  • Workflow-focused tools that enable complete tasks, not just API wrapping
  • Optimized for context efficiency with configurable detail levels
  • Actionable error messages that guide agents toward solutions
  • Natural task subdivisions with intuitive tool naming

Available Tools

📖 get_documentation

Fetch specific sections of React Native Godot documentation:

  • Overview, installation, initialization
  • API usage, threading, views
  • Export, debugging, custom builds
  • Configurable detail levels (concise/detailed/full)

🔍 search_documentation

Intelligent search across all documentation:

  • Keyword-based search with relevance scoring
  • Returns most relevant sections
  • Perfect for finding specific topics or troubleshooting

💻 get_example_code

Retrieve working code examples for:

  • Initialization and setup
  • API usage patterns
  • Signal handling
  • View embedding
  • Worklets and threading
  • Complete application examples

🛠️ get_setup_instructions

Platform-specific setup guidance:

  • iOS and Android configurations
  • Debugging setup options
  • Custom build instructions
  • Step-by-step installation process

📚 get_api_reference

Detailed API documentation for:

  • RTNGodot class methods
  • RTNGodotView component
  • runOnGodotThread function
  • Signals and callables
  • Property access patterns

🔧 get_troubleshooting

Solutions for common issues:

  • Build errors
  • View display problems
  • Threading issues
  • Export problems
  • Performance optimization

📁 get_file_from_repo

Direct access to repository files:

  • Example implementations
  • Configuration files
  • Build scripts
  • Native code

📦 Installation

Prerequisites

# Python 3.8+
python --version

# Install MCP and FastMCP
pip install mcp fastmcp

Install Dependencies

pip install httpx pydantic

Make Executable

chmod +x react_native_godot_mcp.py

🎯 Usage

Running the Server

Standalone Mode

python react_native_godot_mcp.py

With MCP Inspector (for testing)

npx @modelcontextprotocol/inspector python react_native_godot_mcp.py

Integration with Claude Desktop

Add to your Claude configuration file:

MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "react-native-godot": {
      "command": "python",
      "args": ["/path/to/react_native_godot_mcp.py"],
      "env": {}
    }
  }
}

Integration with Other MCP Clients

The server uses stdio transport and can be integrated with any MCP-compatible client:

# Example Python client usage
from mcp import Client

client = Client()
client.connect_stdio(["python", "react_native_godot_mcp.py"])

# Use tools
result = await client.call_tool(
    "get_documentation",
    {"section": "initialization", "detail": "detailed"}
)

💡 Example Queries

Get Started with React Native Godot

# Fetch installation instructions
get_setup_instructions(platform="both", include_debugging=True)

# Get initialization example
get_example_code(topic="initialization", platform="ios")

Search for Specific Topics

# Search for worklet information
search_documentation(query="worklets threading", max_results=5)

# Find signal handling docs
search_documentation(query="connect signals JavaScript")

Troubleshoot Issues

# Get help with build errors
get_troubleshooting(issue="build_error", platform="android")

# Debug view problems
get_troubleshooting(issue="view_not_showing")

Deep Dive into API

# Get RTNGodot API reference
get_api_reference(topic="RTNGodot", include_examples=True)

# Learn about signals
get_api_reference(topic="signals")

🧪 Running Evaluations

The repository includes comprehensive evaluation questions to test the MCP server's capabilities.

Using the Evaluation File

  1. The evaluation file (react_native_godot_evaluation.xml) contains 10 complex questions
  2. Each question tests the server's ability to find specific information
  3. Questions cover initialization, threading, debugging, API usage, and more

Running Evaluations with MCP

# Install evaluation tools
pip install mcp-eval

# Run evaluation
mcp-eval run react_native_godot_mcp.py react_native_godot_evaluation.xml

Manual Testing

You can manually test each tool:

# Test documentation fetching
python -c "
import asyncio
from react_native_godot_mcp import get_documentation

async def test():
    result = await get_documentation(None, 'threading', 'markdown', 'detailed')
    print(result)

asyncio.run(test())
"

🏗️ Architecture

Design Principles

  1. Workflow-Oriented: Tools are designed around common developer workflows
  2. Context-Aware: Adjustable detail levels to optimize token usage
  3. Error-Resilient: Graceful handling with actionable error messages
  4. Format-Flexible: Supports both Markdown and JSON responses

Response Formats

All tools support two response formats:

  • Markdown: Human-readable, formatted documentation
  • JSON: Structured data for programmatic use

Detail Levels

Three levels of detail for documentation:

  • Concise: Key points and headers only
  • Detailed: Standard documentation with examples
  • Full: Complete content including all details

🔒 Security & Limits

  • Character Limit: 25,000 characters per response
  • Request Timeout: 30 seconds
  • Max Search Results: 20 per query
  • Rate Limiting: Respects GitHub API limits

🤝 Contributing

This MCP server is designed to be extensible. To add new features:

  1. Add new tool methods with @mcp.tool decorator
  2. Define Pydantic input models for validation
  3. Follow the existing patterns for error handling
  4. Add corresponding evaluation questions

📄 License

MIT License - Same as React Native Godot

🙏 Credits

  • React Native Godot: Created by Born and Migeran
  • MCP Server: Built using the Model Context Protocol by Anthropic
  • FastMCP: Simplified MCP development framework

📞 Support

For React Native Godot questions:

For MCP server issues:

  • Open an issue in this repository
  • Check the evaluation results for capability verification

🚦 Status

  • ✅ All documentation sections accessible
  • ✅ Intelligent search functionality
  • ✅ Complete example code coverage
  • ✅ Platform-specific guidance
  • ✅ Comprehensive troubleshooting
  • ✅ Direct file access from repository
  • ✅ 10 evaluation questions for testing

Built with ❤️ for the React Native and Godot communities

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选