A template project demonstrating interaction between a TypeScript-based MCP server and a Unity client.
This is a simple example project demonstrating interaction between a TypeScript-based MCP server and Unity. You can build and configure your own tools to expand and develop further.
Create more tools your own!
unity-mcp-sample is a Unity example project. To minimize version-related issues and ensure compatibility with legacy versions, it does not use packages like NewtonsoftJSON. Additionally, the EditorWindow is implemented using IMGUI. The MCP can be managed through the UnityMCP-ShowWindow at the top.
within the unity-mcp-server
npm install
npm run build
Open Claude Desktop Settings, and Developer-Edit Config
{
"mcpServers": {
"unity-mcp": {
"command": "node",
"args":["F:/unity-mcp-template/unity-mcp-server/dist/index.js"]
}
}
}
Both input data structure should be same.
Refer to CreateObjectTools and create the tool you want.
Refer to createObject and create the tool you want.
Remote, no-auth MCP server providing AI-powered codebase context and answers
Search dashboards, investigate incidents and query datasources in your Grafana instance
Reference / test server with prompts, resources, and tools
A GraphQL server that supports the Model Context Protocol (MCP), enabling Large Language Models (LLMs) to interact with GraphQL APIs through schema introspection and query execution.
Client implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.
Provides seamless integration with SonarQube Server or Cloud, and enables analysis of code snippets directly within the agent context
Automatically builds and serves context files from codebases for AI assistants like Claude.
Server for advanced AI-driven video editing, semantic search, multilingual transcription, generative media, voice cloning, and content moderation.
Explore and analyze OpenAPI specifications from local files or remote URLs.
An MCP server that integrates with Ollama to provide tools for file operations, calculations, and text processing. Requires a running Ollama instance.