Unity-MCP and unity-api-mcp
These are complements: the first provides a general LLM-to-Unity bridge for code generation and automation, while the second optimizes that bridge by replacing expensive source file reads with efficient API lookups, reducing token consumption and hallucinations in the agent's context window.
About Unity-MCP
IvanMurzak/Unity-MCP
AI-powered bridge connecting LLMs and advanced AI agents to the Unity Editor via the Model Context Protocol (MCP). Chat with AI to generate code, debug errors, and automate game development tasks directly within your project.
Implements MCP server architecture running both in the Unity Editor and compiled runtime, supporting stdio-based local execution and HTTP-based remote deployment without vendor lock-in. Generates dynamic "skills" metadata reflecting project state (Unity version, OS, installed plugins) to enhance LLM context, and provides extensible MCP Tools for editor automation alongside in-game runtime capabilities for NPC behavior and live debugging. Compatible across multiple AI clients (Claude, Cursor, GitHub Copilot, VS Code, Rider) and deployable via npm CLI, Docker, or direct UPM package integration.
About unity-api-mcp
Codeturion/unity-api-mcp
Instant, accurate Unity API lookups instead of expensive source file reads, saving your agent tokens, context, and hallucinations
Implements an MCP server with version-specific SQLite databases (~18–24 MB each) for Unity 2022, 2023, and 6, parsed from official XML documentation and C# source. Provides five tools—search, method signatures, namespace resolution, class references, and deprecation checks—all returning results in <15ms with BM25-ranked search and tuned column weights. Integrates with Claude Code, Cursor, Windsurf, and any MCP client; auto-detects Unity version from `ProjectSettings/ProjectVersion.txt` or explicit environment variables.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work