unity-mcp-operations

Solid

Use when operating Unity Biome MCP to select or discover tools, batch compatible commands, resolve schemas, reduce response size, or recover a connection or session.

AI & Automation 27 stars 4 forks Updated today MIT

Install

View on GitHub

Quality Score: 82/100

Stars 20%
48
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Unity MCP Operations Use this skill as the shared operating contract for every Unity Biome MCP task. The live server schema and the current Unity state are authoritative. ## Core Workflow 1. Confirm the server and Editor state with `mcp_status` when connectivity or mode is uncertain. 2. Read the smallest useful scope. Start with a hierarchy summary, targeted `inspect`, or one component rather than a full-scene dump. 3. Enable a gated category with its uppercase canonical name: `SCENE`, `COMPONENTS`, `ASSETS`, `MEDIA`, `UGUI`, `UITOOLKIT`, `VERIFY`, `RUNTIME`, `TESTS`, or `SYSTEM`. For UI use the specific alias: `discover_tools("ugui")` or `discover_tools("uitoolkit")`. 4. Call `resolve_tool_schema(tools="<name>")` before relying on a parameter you have not used in the current session. Do not reconstruct signatures from memory. 5. Mark the console before mutations when new errors would matter. 6. Choose the narrowest aggregate tool that expresses the operation. 7. Mutate, verify the changed state, and report evidence rather than a list of calls. Before rebuilding a known repeated workflow, call `list_skills()`. Reuse a matching learned MCP skill with `use_skill(...)` when its stored contract still matches the current scene and schema. ## Routing | Need | Prefer | |---|---| | Same component across multiple objects | `inspect(paths=..., components=..., fields=...)` | | Create several ordinary objects | `setup_objects(specs=...)` as a standalone ca...

Details

Author
german-krasnikov
Repository
german-krasnikov/unity-biome-mcp
Created
2 months ago
Last Updated
today
Language
C#
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category