Automates Unity workflows and manipulates assets using local large language models via Ollama.
If you already use Unity Ollama, the unity ollama mcp server is the piece that lets your assistant work with it directly. Automates Unity workflows and manipulates assets using local large language models via Ollama.
A Unity MCP (Model Context Protocol) package that enables seamless communication between Unity and local Large Language Models (LLMs) via Ollama. This package extends justinpbarnett/unity-mcp to work with local LLMs, allowing developers to automate workflows, manipulate assets, and control the Unity Editor programmatically without relying on cloud-based LLMs.
The Unity MCP with Ollama Integration provides a bidirectional communication channel between:
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
deepseek-r1 — 14b** - A 14 billion parameter model with strong reasoning capabilitiesgemma3 — 12b** - Google's 12 billion parameter model with good general capabilitiesHost — localhost (default)Port — 11434 (default)Model — Select either deepseek-r1:14b or gemma3:12bTemperature — Adjust as needed (0.0-1.0)Green — ConnectedYellow — Connected but with issuesRed — Not connectedRunning — Unity is listening for connectionsStopped — Unity socket server is not activeConnected — Successfully connected to Ollama serverSetup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client.
ollama pull deepseek-r1:14b - ollama pull gemma3:12bAmong the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Unity Ollama's toolset — deepseek-r1, gemma3, Host and 11 more — is a fair guide to whether it matches your workflow. It is maintained by ZundamonnoVRChatkaisetu; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| deepseek-r1 | 14b** - A 14 billion parameter model with strong reasoning capabilities |
| gemma3 | 12b** - Google's 12 billion parameter model with good general capabilities |
| Host | localhost (default) |
| Port | 11434 (default) |
| Model | Select either deepseek-r1:14b or gemma3:12b |
| Temperature | Adjust as needed (0.0-1.0) |
| Green | Connected |
| Yellow | Connected but with issues |
| Red | Not connected |
| Running | Unity is listening for connections |
| Stopped | Unity socket server is not active |
| Connected | Successfully connected to Ollama server |
| CPU | only operation is possible but will be significantly slower |
| Prerequisites | The Prerequisites tool exposed by this server. |
ollama pull deepseek-r1:14b - ollama pull gemma3:12bKill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.