[Back to MCP overview](https://www.summerengine.com/mcp)

Summer Engine MCP guide

# How to make games with Ollama and Summer Engine

Run a free local model with Ollama and drive Summer Engine through MCP — a real desktop game engine, no AI subscription required. Summer Engine is the desktop game engine; Ollama drives it through MCP with a model running on your own hardware.

$ npx -y summer-engine@latest setup opencode --yes

Ollama runs the model free on your GPU. Summer Engine shows the game.

01

## Summer is free for MCP use

Download the desktop engine and connect it to your agent. The model runs on your own hardware, with no AI subscription and no per-message cost.

02

## Open Ollama

Run a free local model on your own GPU. The setup writes the MCP config so {agentLabel} can drive the engine directly.

03

## Run a Summer game

The local model writes code. Summer Engine shows the Summer game, runs Play mode, and helps inspect errors. Export still requires the target templates and toolchains.

Install

## Connect Summer to Ollama

1. 1  
### Install Summer Engine  
Downloads the desktop engine app, about 1 GB. Skip it if Summer Engine is already installed, or if you only need assets and video for a game built in another engine.  
$ npx -y summer-engine@latest install
2. 2  
### Sign in  
Opens your browser once. The CLI and the engine share the session.  
$ npx -y summer-engine@latest login
3. 3  
### Connect Ollama  
Writes the summer-engine MCP config and installs the Summer game-dev skills.  
$ npx -y summer-engine@latest setup opencode --yes
4. 4  
### Restart and build  
Ollama serves the model but is not an MCP client by itself. Pair it with OpenCode (terminal), Kilo Code (VS Code), or Goose — the setup command above wires OpenCode, the most common pairing in 2026\. Point its provider at http://localhost:11434/v1.

Local setup notes

## The 2026 specifics.

### Pair Ollama with an MCP agent

Ollama serves the model but is not an MCP client by itself. Pair it with OpenCode (terminal), Kilo Code (VS Code), or Goose — the setup command above wires OpenCode, the most common pairing in 2026\. Point its provider at http://localhost:11434/v1.

### Fix the context window first

Ollama defaults to a 4k context on GPUs under 24 GB of VRAM, and MCP tool schemas alone can overflow that — the failure is silent. Start the server with OLLAMA\_CONTEXT\_LENGTH=65536 (or raise the slider in the Ollama app), then run \`ollama ps\` to confirm the model still fits on the GPU.

### Models that hold up

Tool calling is the hard part for local models. Safe picks in mid-2026: gpt-oss-20b on 12–16 GB cards, Qwen3-Coder-30B or Gemma 4 27B on 24 GB. Use Q4\_K\_M quantization or better — heavier quantization breaks tool calls before it breaks chat.

Why this matters

## Ollama runs free on your hardware. Summer Engine shows the game.

A capable local model can operate a real engine through MCP. It opens scenes, places objects, runs the project and reads errors. Your GPU does the thinking, with no subscription and no per-token bill, and your prompts never leave your machine.

Other setup guides

## Start with Ollama. Build inside Summer.

Install the desktop app for free, connect the MCP server, and make your first scene playable. No subscription required.

[Download](https://www.summerengine.com/download)

[Docs ](https://docs.summerengine.com/mcp/overview)

Source: https://www.summerengine.com/mcp/how-to-make-games-with-ollama

---

## Machine-readable resources

- Site index for agents: https://www.summerengine.com/llms.txt
- Full inlined content: https://www.summerengine.com/llms-full.txt
- Porting catalog: https://www.summerengine.com/llms-porting.txt
- Structured catalog: https://www.summerengine.com/agent-catalog.json
- Sitemap: https://www.summerengine.com/sitemap.xml
- Developer resources: https://www.summerengine.com/docs