unity-mcp-plugin

Provides a Unity Editor HTTP bridge (localhost:7890) that exposes a large set of MCP tools (268 across 30+ categories) via a companion MCP server, enabling AI assistants to inspect and modify Unity projects (scenes, GameObjects, components, assets, scripts, builds, editor/play mode actions, profiling/debugging, shaders, terrain, navigation, etc.).

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ DevTools unity mcp editor-automation ai-assisted-development csharp game-development local-http-bridge tooling
⚙ Agent Friendliness
59
/ 100
Can an agent use this?
🔒 Security
23
/ 100
Is it safe for agents?
⚡ Reliability
21
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
70
Error Messages
0
Auth Simplicity
100
Rate Limits
20

🔒 Security

TLS Enforcement
20
Auth Strength
10
Scope Granularity
0
Dep. Hygiene
30
Secret Handling
60

Security model is described as localhost-only binding (127.0.0.1) with no authentication. TLS is not mentioned (likely plain HTTP). No authorization scopes or per-tool permission model are described. If localhost is exposed via misconfiguration/port forwarding, risk increases substantially. On the dependency side, package manifest shows no npm dependencies, but Unity/C# dependencies are not assessed from provided data.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
0
Error Recovery
45
AF Security Reliability

Best When

You have an MCP-compatible AI assistant and a local Unity Editor workflow where low-latency editor control is acceptable and you trust the local assistant/session.

Avoid When

You need strong access control, multi-user isolation, or exposure beyond the local machine; or you cannot mitigate risk from any local process that can reach localhost:7890.

Use Cases

  • AI-assisted creation and editing of Unity scenes and levels
  • Programmatic refactoring/inspection of GameObjects, components, serialized properties
  • Procedural content creation (terrain/terrain layers, trees/detail objects)
  • Automated editor workflows (menu items, project info, compilation errors/logs, test runner)
  • Build automation and profiling/debugging workflows from within the editor

Not For

  • Production-grade remote administration over the public network (no auth described)
  • High-stakes operations requiring strong auditability/approval workflows without further safeguards
  • Environments where localhost-only binding is not guaranteed (e.g., unusual network exposure/forwarding)

Interface

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

Authentication

OAuth: No Scopes: No

README states no authentication is required because the server binds only to 127.0.0.1 (localhost). No API keys/OAuth scopes are described.

Pricing

Free tier: Yes
Requires CC: No

Costs are primarily the connected AI assistant subscription; the MCP plugin itself is described as free/open source.

Agent Metadata

Pagination
unknown
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Local-only security: any process on the host that can reach localhost may potentially interact (no auth described).
  • Editor mutation side effects: retries/timeouts may cause repeated actions (e.g., creating assets/objects) without clear idempotency semantics.
  • Category toggles and optional packages: some tool subsets require additional Unity packages/assets (shadergraph, memoryprofiler, inputsystem, multiplayer.playmode, Amplify Shader Editor).
  • Port management: if multiple Unity editors are running, session/port affinity must be correct to hit the intended instance.

Alternatives

Full Evaluation Report

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