unitypilot
MCP server that lets AI agents drive the full Unity lifecycle on macOS without opening the Unity Editor.
README
UnityPilot
An MCP server that lets an AI agent drive the full Unity lifecycle on macOS — without the developer ever opening the Unity Editor by hand.
One npm install, and an AI agent can install Unity, scaffold a project, launch it (visible
or headless), import assets, build scenes, write & compile scripts, screenshot the view,
read the console, and run tests.
→ User docs, install, and the tool catalog: packages/orchestrator/README.md.
This repo root is for working on UnityPilot itself. See SPEC.md for the full spec and
CLAUDE.md for the working agreement.
⚠️ v1 is macOS only
Apple Silicon (arm64) and Intel (x64) are supported. Windows and Linux exist only as
NotImplemented resolver stubs for contributors to fill in.
Status
Phases 0–6 complete (full lifecycle + the autonomous feedback loop). Phase 7 (packaging +
public release) in progress. Built strictly phase by phase — see SPEC.md §9.
Packages
packages/orchestrator— the Node/TypeScript MCP server (our code), published to npm asunitypilot. Bundles the bridge at pack time.packages/bridge— the forked C# Unity (UPM) bridge, injected into projects via afile:reference. Fork of CoderGamester/mcp-unity (MIT); fork changes inpackages/bridge/FORK.md.
Develop (macOS)
corepack enable pnpm # pnpm 9 ships with Node 22 via corepack
pnpm install
pnpm build
pnpm test
To produce a publishable tarball (copies the bridge into the package, then builds):
cd packages/orchestrator
npm pack # runs prepack: bundle-bridge + tsc
Out of scope for v1
Asset generation, Windows/Linux, Unity Asset Store distribution, and fully autonomous
visual correctness. See SPEC.md §8.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.