unity-mcp-pro-plugin

Unity editor plugin that integrates MCP-compatible AI assistants with the Unity editor by running a WebSocket client inside Unity and dispatching tool calls to Unity-side command handlers (with Undo/Redo and reconnection handling).

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ Ai Ml unity unity-plugin mcp model-context-protocol editor-automation websocket ai-tools csharp nodejs-server local-dev
⚙ Agent Friendliness
53
/ 100
Can an agent use this?
🔒 Security
22
/ 100
Is it safe for agents?
⚡ Reliability
35
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
40
Documentation
65
Error Messages
0
Auth Simplicity
90
Rate Limits
5

🔒 Security

TLS Enforcement
10
Auth Strength
20
Scope Granularity
10
Dep. Hygiene
30
Secret Handling
40

Security details are limited in the provided content. The bridge appears to use a local WebSocket client connecting to localhost (127.0.0.1) on a small port range, but TLS requirements and message authentication are not described. No scope-based authorization or secret-management guidance is provided. Because the plugin can perform editor actions broadly (many tool categories), access control would be important if any component is reachable from outside the local host.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
30
Error Recovery
70
AF Security Reliability

Best When

You want local, iterative AI-driven Unity editing using MCP clients, with Undo/Redo and automatic reconnection for long editor sessions.

Avoid When

You cannot run a local MCP server/WebSocket bridge, or you require strong authentication/authorization and network security guarantees beyond loopback/localhost usage.

Use Cases

  • Use AI assistants to create/modify Unity scenes, GameObjects, components, prefabs, scripts, and assets
  • AI-assisted editor automation (build pipeline, input simulation, screenshots/visual inspection, testing/QA workflows)
  • Rapid iteration of Unity projects (type parsing and Undo/Redo for safe changes)
  • Connecting MCP tools from IDE/assistant clients to a local Unity editor via a WebSocket bridge

Not For

  • Production deployments where editor-side network connectivity is disallowed or tightly restricted
  • Environments requiring strict security controls without additional hardening (auth, network allowlists)
  • Workflows that need a well-defined external REST/SDK interface (this is primarily an editor plugin + local MCP/WebSocket bridge)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
No
SDK
No
Webhooks
No

Authentication

Methods: No authentication described for the Unity editor WebSocket client/bridge (local MCP server implied)
OAuth: No Scopes: No

Authentication/authorization is not described in the provided README content; tool access appears to rely on the local MCP server and editor-side connection.

Pricing

Free tier: No
Requires CC: No

No pricing information provided in the README/manifest content.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Documented

Known Gotchas

  • Multi-editor support uses a port range (6605–6609) and optional UNITY_MCP_PORT; agents may connect to the wrong Unity instance if environment/port selection is misconfigured.
  • Auto-reconnect is mentioned, but there is no documented guidance on how agents should handle in-flight tool calls after disconnects/retries.
  • No authentication/authorization is described; if the MCP server/WebSocket is exposed beyond localhost, agents may be able to invoke tools unexpectedly.
  • Undo/Redo exists, but agents may still need to be careful about composing multiple changes as a single logical edit.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for unity-mcp-pro-plugin.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered