Skip to main content
mcpSource-backed

Unity MCP Server

Unity Editor MCP bridge that lets AI assistants manage assets, edit scripts, control scenes, run tests, and automate Unity workflows through the Model Context Protocol.

by CoplayDev · submitted by oktofeesh1·added 2026-06-06·
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://coplaydev.github.io/unity-mcp/, https://github.com/CoplayDev/unity-mcp
Brand
Unity MCP
Brand domain
github.com
Safety notes
Unity MCP can create, modify, delete, and inspect Unity project assets, scenes, scripts, tests, editor state, and generated files., Agents may execute Unity Editor actions that trigger imports, compilation, play mode, tests, package changes, or custom editor scripts., Use tool groups and project-level scoping to limit which Unity workflows an agent can access., Test automation in a disposable project before connecting the server to production game, simulation, AR, VR, or client work., Remote server auth and multi-instance routing should be configured carefully so an agent controls only the intended Unity Editor instance.
Privacy notes
Scene names, asset paths, scripts, serialized object data, test results, editor logs, package metadata, and project structure may be exposed to the MCP client and model., Unity projects can contain proprietary artwork, gameplay systems, licensed assets, unpublished game logic, client IP, and credentials embedded in editor tooling., Remote server mode may expose project context over the network; require authentication and avoid sharing endpoints beyond trusted clients., Review generated scripts and asset changes before committing, shipping, or syncing them to shared repositories.
Author
CoplayDev
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-06

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

63

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as source-backed.

    Done
  • Metadata reviewed

    No reviewed flag detected in metadata.

    Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    No package verification flag provided.

    Pending
  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

15 minutes

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    No review metadata found; increase manual validation.

    Pending
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

Prerequisite readiness

5 prerequisites to line up before setup.

0/5 ready
Install & runtime2Permissions & scopes1Network & hosting1General115 minutes

Safety & privacy surface

Safety & privacy surface

5 safety and 4 privacy notes across 5 risk areas. Review closely: credentials & tokens, network access.

5 areas
  • SafetyLocal filesUnity MCP can create, modify, delete, and inspect Unity project assets, scenes, scripts, tests, editor state, and generated files.
  • SafetyExecution & processesAgents may execute Unity Editor actions that trigger imports, compilation, play mode, tests, package changes, or custom editor scripts.
  • SafetyGeneralUse tool groups and project-level scoping to limit which Unity workflows an agent can access.
  • SafetyGeneralTest automation in a disposable project before connecting the server to production game, simulation, AR, VR, or client work.
  • SafetyNetwork accessRemote server auth and multi-instance routing should be configured carefully so an agent controls only the intended Unity Editor instance.
  • PrivacyLocal filesScene names, asset paths, scripts, serialized object data, test results, editor logs, package metadata, and project structure may be exposed to the MCP client and model.
  • PrivacyCredentials & tokensUnity projects can contain proprietary artwork, gameplay systems, licensed assets, unpublished game logic, client IP, and credentials embedded in editor tooling.
  • PrivacyNetwork accessRemote server mode may expose project context over the network; require authentication and avoid sharing endpoints beyond trusted clients.
  • PrivacyExecution & processesReview generated scripts and asset changes before committing, shipping, or syncing them to shared repositories.

Safety notes

  • Unity MCP can create, modify, delete, and inspect Unity project assets, scenes, scripts, tests, editor state, and generated files.
  • Agents may execute Unity Editor actions that trigger imports, compilation, play mode, tests, package changes, or custom editor scripts.
  • Use tool groups and project-level scoping to limit which Unity workflows an agent can access.
  • Test automation in a disposable project before connecting the server to production game, simulation, AR, VR, or client work.
  • Remote server auth and multi-instance routing should be configured carefully so an agent controls only the intended Unity Editor instance.

Privacy notes

  • Scene names, asset paths, scripts, serialized object data, test results, editor logs, package metadata, and project structure may be exposed to the MCP client and model.
  • Unity projects can contain proprietary artwork, gameplay systems, licensed assets, unpublished game logic, client IP, and credentials embedded in editor tooling.
  • Remote server mode may expose project context over the network; require authentication and avoid sharing endpoints beyond trusted clients.
  • Review generated scripts and asset changes before committing, shipping, or syncing them to shared repositories.

Prerequisites

  • Unity Editor installed with a project you are authorized to modify.
  • Unity Package Manager access to add a package from a git URL, or another install path documented by the project.
  • Python 3.10 or newer for the MCP server side documented by the project.
  • MCP-capable client such as Claude, Codex, VS Code, Cursor, or another supported host.
  • Version control, backups, or a disposable test Unity project before allowing an agent to edit scenes, scripts, or assets.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
15 minutes
Difficulty
intermediate
Full copyable content
https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main

About this resource

Content

Unity MCP Server bridges MCP-compatible AI assistants to the Unity Editor. It lets agents inspect and automate Unity workflows such as managing assets, controlling scenes, editing scripts, running tests, and authoring project content from natural-language prompts.

The project provides a Unity package, a Python MCP server component, docs for first-run setup, and guides for multi-instance routing, tool groups, Roslyn validation, and remote server authentication.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository and documentation for current Unity package URLs, beta channel guidance, server commands, supported clients, release notes, and remote authentication behavior.

Features

  • Connect MCP clients to a running Unity Editor project.
  • Create and modify Unity scenes, objects, assets, and scripts.
  • Run tests and automate project workflows from an agent.
  • Configure detected clients from the Unity Editor menu.
  • Use tool groups to control which categories of Unity tools are exposed.
  • Route multiple Unity instances to the intended client/server pairing.
  • Support remote-hosted server setups with authentication.
  • Provide docs for first prompts, installation channels, and development setup.

Installation

Install the Unity package through Unity Package Manager by adding the git URL:

https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main

For the beta channel, use the upstream beta branch guidance from the docs.

After the package is installed, open the Unity Editor menu and run:

Window > MCP for Unity > Configure All Detected Clients

Then verify the server from your MCP client and start with a small disposable scene change before using it in a production project.

For stdio MCP clients, the upstream server package documents this command:

uvx --from mcpforunityserver mcp-for-unity --transport stdio

Use Cases

  • Prototype Unity scenes and object layouts from Claude or another MCP client.
  • Generate or revise Unity scripts while keeping the Editor in the loop.
  • Automate repetitive asset, scene, and test workflows.
  • Inspect Unity project structure before changing gameplay code.
  • Route several Unity Editor instances during multi-project development.
  • Limit exposed capabilities with tool groups for safer agent workflows.

Safety and Privacy

Unity MCP gives an agent real editing power inside a Unity project. Treat it as write-capable project automation, not as a passive documentation source. Use a throwaway project first, keep version control clean, review diffs, and require human approval before broad asset, scene, package, or script changes.

Projects may include unreleased game design, proprietary assets, client work, licensed store content, credentials in editor tooling, analytics keys, and internal build scripts. Connect only trusted MCP clients and avoid remote access unless authentication, network exposure, and instance routing are configured deliberately.

Duplicate Check

No CoplayDev/unity-mcp entry, Unity MCP entry, or matching Unity MCP source URL was found in content/mcp.

Source citations

Add this badge to your README

Show that Unity MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/unity-mcp-server.svg)](https://heyclau.de/entry/mcp/unity-mcp-server)

How it compares

Unity MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field

Unity Editor MCP bridge that lets AI assistants manage assets, edit scripts, control scenes, run tests, and automate Unity workflows through the Model Context Protocol.

Open dossier

Unity MCP server, plugin, CLI, and skill generator for controlling Unity Editor and runtime projects from MCP clients through built-in game-dev tools.

Open dossier

Unity Editor MCP bridge from CoderGamester that lets Claude and other MCP clients inspect scenes, manage GameObjects, edit components and materials, run tests, read console logs, and automate Unity project workflows through a Node.js stdio server connected to a Unity WebSocket bridge.

Open dossier

Official MCP server for agent-device, Callstack's device automation CLI for inspecting, controlling, debugging, recording, and collecting evidence from iOS, Android, TV, macOS, Linux, React Native, Expo, Flutter, and native apps.

Open dossier
Next steps
Trust
Review statusNot reviewedNot reviewedNot reviewedNot reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
Submitteroktofeesh1oktofeesh1oktofeesh1oktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandAI Game Developer logoAI Game Developeragent-device logoagent-device
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthorCoplayDevIvan MurzakCoderGamesterCallstack
Added2026-06-062026-06-062026-06-062026-06-06
Platforms
Harness
Source repo
Safety notesUnity MCP can create, modify, delete, and inspect Unity project assets, scenes, scripts, tests, editor state, and generated files. Agents may execute Unity Editor actions that trigger imports, compilation, play mode, tests, package changes, or custom editor scripts. Use tool groups and project-level scoping to limit which Unity workflows an agent can access. Test automation in a disposable project before connecting the server to production game, simulation, AR, VR, or client work. Remote server auth and multi-instance routing should be configured carefully so an agent controls only the intended Unity Editor instance.AI Game Developer can create, move, copy, modify, and delete Unity assets, scenes, GameObjects, components, scripts, packages, and generated project files. Tools include dynamic C# script execution, C# reflection method lookup and calls, package installation/removal, Unity test execution, editor state changes, play mode control, screenshots, and profiler access. The MCP server supports streamable HTTP and stdio; HTTP deployments should require a bearer token and stay bound to trusted interfaces. Server variables include optional authorization and webhook settings; webhook endpoints can receive tool, prompt, resource, connection, and authorization events. Unity runtime connections can expose compiled game state or in-game behavior to an MCP client, not just editor-only project data. Use source control, backups, tool filtering, and explicit review before allowing destructive tools such as asset deletion, package removal, script execution, or reflection calls.MCP Unity can create, update, duplicate, move, rotate, scale, reparent, and delete GameObjects, scenes, materials, prefabs, components, and packages in the active Unity project. Unity Editor actions can trigger imports, script compilation, package installs, tests, play-mode reloads, custom menu items, or project-specific editor scripts. The Unity-side WebSocket bridge defaults to localhost, but the README documents optional remote connections; expose remote host or port settings only on trusted networks. Re-run the Unity client configuration after package updates because Unity Package Manager cache paths include a changing package hash. Review batched operations carefully because a single MCP call can execute multiple Unity actions.Agent Device MCP exposes structured tools backed by `AgentDeviceClient`; the docs state it does not expose generic shell execution over MCP. Tools and CLI workflows can open apps, inspect UI, tap, type, scroll, perform gestures, wait, assert state, handle alerts, and close sessions. Evidence workflows can capture screenshots, recordings, logs, traces, network traffic, performance samples, crash context, React profiles, and replay files. Mutating commands should run serially against one session, and separate sessions or devices should be used for parallel work. Prefer dedicated test devices or simulators, and require approval before entering credentials, submitting forms, changing settings, installing apps, sending messages, or touching production accounts.
Privacy notesScene names, asset paths, scripts, serialized object data, test results, editor logs, package metadata, and project structure may be exposed to the MCP client and model. Unity projects can contain proprietary artwork, gameplay systems, licensed assets, unpublished game logic, client IP, and credentials embedded in editor tooling. Remote server mode may expose project context over the network; require authentication and avoid sharing endpoints beyond trusted clients. Review generated scripts and asset changes before committing, shipping, or syncing them to shared repositories.Tool calls may expose Unity project paths, asset names, scene hierarchy, serialized object data, scripts, logs, screenshots, profiler metrics, test output, package metadata, and runtime state. MCP config files and Unity plugin config can contain server URLs, connection modes, bearer tokens, authorization settings, enabled tool IDs, and cloud or local endpoint details. Optional webhooks can receive tool, prompt, resource, connection, authorization, and token-bearing request data. Screenshots from Game View, Scene View, cameras, or isolated GameObjects may include proprietary artwork, level design, UI, debug overlays, or unreleased game content. Generated skills and AI-client configuration files can reveal available tools, project structure, installed packages, and local workflow assumptions.Unity projects can contain proprietary game logic, unreleased assets, licensed packages, customer IP, local paths, console logs, test names, build settings, and credentials embedded in custom tooling. MCP resources can expose scene hierarchy, GameObject details, package lists, assets, tests, and console logs to the MCP client and model. Console logs and generated error traces may include file paths, stack traces, tokens, URLs, player data, analytics IDs, or internal service names. If remote bridge connections are enabled, protect the Unity host and WebSocket port with network controls and avoid exposing the editor to untrusted machines.Screenshots, recordings, traces, logs, network dumps, replay files, reports, UI snapshots, typed input, and React profiles can contain private UI state, tokens, request data, customer information, or credentials. macOS, iOS, Android, and TV automation can expose local app state, notifications, device names, package identifiers, app content, system dialogs, and permission prompts. Network inspection artifacts may include headers, payloads, session identifiers, URLs, and API data; review before sharing or committing. Interactive CLI runs may check npm for newer package versions unless `AGENT_DEVICE_NO_UPDATE_NOTIFIER=1` is set.
Prerequisites
  • Unity Editor installed with a project you are authorized to modify.
  • Unity Package Manager access to add a package from a git URL, or another install path documented by the project.
  • Python 3.10 or newer for the MCP server side documented by the project.
  • MCP-capable client such as Claude, Codex, VS Code, Cursor, or another supported host.
  • Unity project using Unity 2022.3 or newer for the current package metadata.
  • Unity Hub or a local Unity Editor installation.
  • Node.js 20.19 or newer, or Node.js 22.12 or newer, for `unity-mcp-cli`.
  • An MCP client such as Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, GitHub Copilot, Cline, or another supported client.
  • Unity Editor project you are authorized to inspect and modify.
  • Review of the current upstream Unity version requirement before installing; the README and package manifest should be treated as the source of truth.
  • Node.js available for the package's Node-based MCP bridge.
  • Unity Package Manager access to add the package from the repository git URL.
  • Node.js 22 or newer and `agent-device` installed globally or project-locally.
  • Xcode tooling for iOS, tvOS, or macOS targets, or Android SDK and ADB for Android targets.
  • Device, simulator, emulator, TV, macOS, or Linux desktop target that the agent is allowed to automate.
  • Required local permissions such as Android device trust, iOS Developer Mode, macOS Accessibility, and Screen Recording where applicable.
Install
Add https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main through Unity Package Manager, then run Window > MCP for Unity > Configure All Detected Clients.
npm install -g unity-mcp-cli && unity-mcp-cli install-plugin ./MyUnityProject
Add https://github.com/CoderGamester/mcp-unity.git through Unity Package Manager, then configure the client from Tools > MCP Unity > Server Window.
claude mcp add --transport stdio --scope user agent-device -- agent-device mcp
Config
{
  "mcpServers": {
    "UnityMCP": {
      "command": "uvx",
      "args": [
        "--from",
        "mcpforunityserver",
        "mcp-for-unity",
        "--transport",
        "stdio"
      ]
    }
  }
}
Manual-only setup:
npm install -g unity-mcp-cli
unity-mcp-cli install-plugin ./MyUnityProject
unity-mcp-cli open ./MyUnityProject
{
  "mcpServers": {
    "mcp-unity": {
      "command": "node",
      "args": ["Library/PackageCache/com.gamelovers.mcp-unity@<hash>/Server~/build/index.js"],
      "env": {
        "UNITY_HOST": "localhost",
        "UNITY_PORT": "8090"
      }
    }
  }
}
{
  "mcpServers": {
    "agent-device": {
      "command": "agent-device",
      "args": ["mcp"]
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.