unity-api-mcp

MCP server that gives AI agents accurate Unity API documentation. Prevents hallucinated signatures, wrong namespaces, and deprecated API usage.

Supports Unity 2022 LTS, 2023, and Unity 6 with separate databases for each version. Works with Claude Code, Cursor, Windsurf, or any MCP-compatible AI tool. No Unity installation required.

Quick Start

Add to your MCP config (.mcp.json, mcp.json, or your tool's MCP settings), setting UNITY_VERSION to match your project:

{
  "mcpServers": {
    "unity-api": {
      "command": "uvx",
      "args": ["unity-api-mcp"],
      "env": {
        "UNITY_VERSION": "2022"
      }
    }
  }
}

Valid values: "2022", "2023", or "6".

On first run the server downloads the correct database (~18-24 MB) to ~/.unity-api-mcp/.

How It Works

1. Version detection. The server figures out which Unity version to serve:

2. Database download. If the database for that version isn't cached locally, it downloads from GitHub (one time).

3. Serve. All tool calls query the version-specific SQLite database. Every query returns in <15ms.

Each version has its own database with the correct signatures, deprecation warnings, and member lists for that release.

Tools

Coverage

All UnityEngine and UnityEditor modules, plus packages parsed from C# source: Input System, Addressables, uGUI, TextMeshPro, AI Navigation, and Netcode.

Does not cover third-party assets (DOTween, VContainer, Newtonsoft.Json). For those, rely on project source.

Benchmarks

In a 10-step research workflow, MCP uses 4x fewer tokens than a skilled agent and 11x fewer than a naive agent:

The gap holds across every question type. MCP wins on simple lookups and complex multi-part research alike:

Even in a realistic hybrid workflow where MCP results are followed up with targeted file reads, it still uses 54% fewer tokens than a skilled agent working without MCP:

"Without MCP" estimates assume full file reads. A skilled agent with good tooling may use fewer tokens than shown. What MCP guarantees is a correct, structured answer in 1 call every time.

Per-question breakdown

Ranking uses BM25 with tuned column weights (member name 10x, class name 5x) plus core namespace boosting to ensure Object.Instantiate ranks above niche APIs like InstantiationParameters.Instantiate.

CLAUDE.md Snippet

Add this to your project's CLAUDE.md (or equivalent instructions file). This step is important. Without it, the AI has the tools but won't know when to reach for them.

## Unity API Lookup (unity-api MCP)

Use the `unity-api` MCP tools to verify Unity API usage instead of guessing. **Do not hallucinate signatures.**

| When | Tool | Example |
|------|------|---------|
| Unsure about a method's parameters or return type | `get_method_signature` | `get_method_signature("UnityEngine.Tilemaps.Tilemap.SetTile")` |
| Need the `using` directive for a type | `get_namespace` | `get_namespace("SceneManager")` |
| Want to see all members on a class | `get_class_reference` | `get_class_reference("InputAction")` |
| Searching for an API by keyword | `search_unity_api` | `search_unity_api("async load scene")` |
| Checking if an API is deprecated | `get_deprecation_warnings` | `get_deprecation_warnings("FindObjectOfType")` |

**Rules:**
- Before writing a Unity API call you haven't used in this conversation, verify the signature with `get_method_signature`
- Before adding a `using` directive, verify with `get_namespace` if unsure
- Covers: all UnityEngine/UnityEditor modules, Input System, Addressables
- Does NOT cover: DOTween, VContainer, Newtonsoft.Json (third-party)

Setup Details

Instead of setting UNITY_VERSION, you can point to your Unity project. The server reads ProjectSettings/ProjectVersion.txt automatically:

{
  "mcpServers": {
    "unity-api": {
      "command": "uvx",
      "args": ["unity-api-mcp"],
      "env": {
        "UNITY_PROJECT_PATH": "/path/to/your/unity-project"
      }
    }
  }
}

Using pip install:

pip install unity-api-mcp

{
  "mcpServers": {
    "unity-api": {
      "command": "unity-api-mcp",
      "args": [],
      "env": {
        "UNITY_VERSION": "2022"
      }
    }
  }
}

If you want to build a database from your own Unity installation instead of downloading:

# Install with ingest dependencies
pip install unity-api-mcp[ingest]

# Build for a specific version
python -m unity_api_mcp.ingest --unity-version 6 --unity-install "D:/Unity/6000.3.8f1" --project "F:/Unity Projects/MyProject"
python -m unity_api_mcp.ingest --unity-version 2022 --unity-install "D:/Unity/2022.3.62f1"
python -m unity_api_mcp.ingest --unity-version 2023 --unity-install "D:/Unity/2023.1.22f1"

Databases are written to ~/.unity-api-mcp/unity_docs_{version}.db by default.

If an AI agent is setting this up for you:

Add unity-api-mcp to my MCP config using uvx with UNITY_VERSION set to match my project, append the CLAUDE.md snippet from the README, and verify with get_namespace("SceneManager").

unity-api-mcp/
├── src/unity_api_mcp/
│   ├── server.py          # MCP server (5 tools)
│   ├── db.py              # SQLite + FTS5 database layer
│   ├── version.py         # Version detection + DB download
│   ├── xml_parser.py      # Parse Unity XML IntelliSense files
│   ├── cs_doc_parser.py   # Parse C# doc comments from package source
│   ├── unity_paths.py     # Locate Unity install + package dirs
│   └── ingest.py          # CLI ingestion pipeline
└── pyproject.toml

Databases are stored in ~/.unity-api-mcp/ (downloaded on first run).

Troubleshooting

See Also

unreal-api-mcp — Same concept for Unreal Engine (C++). Covers UE 5.5, 5.6, and 5.7.

Contact

Need a custom MCP server for your engine or framework? I build MCP tools that cut token waste and prevent hallucinations for AI-assisted game development. If you want something similar for your team's stack, reach out.

fuatcankoseoglu@gmail.com

License

PolyForm Noncommercial 1.0.0

Free to use, fork, modify, and share for any personal or non-commercial purpose. Commercial use requires permission.