Kursach_StealthAction/.agent/skills/tool-set-enabled-state/SKILL.md

name	description	metadata
tool-set-enabled-state	Enable or disable MCP tools by name in batch. Persists the change via `UnityMcpPluginEditor.Instance.Save()` only when at least one tool actually flipped. Returns per-input success flags plus optional operation logs.	generated-by mcp-plugin-dotnet

Tool / Set Enabled State

Enable or disable MCP tools by name. Allows controlling which tools are available for the AI agent.

Inputs

• tools — array of ToolToggleInput { Name, Enabled }. Non-empty.
• includeLogs (default false) — when true, returns per-step operation logs alongside the success map.

Behavior

Each entry is resolved against the tool manager's exact-name and case-insensitive lookups. Already-correct state short-circuits as success without writing. The plugin's config is saved once at the end iff at least one tool actually changed state.

How to Call

unity-mcp-cli run-tool tool-set-enabled-state --input '{
  "tools": "string_value",
  "includeLogs": false
}'

For complex input (multi-line strings, code), save the JSON to a file and use:

unity-mcp-cli run-tool tool-set-enabled-state --input-file args.json

Or pipe via stdin (recommended):

unity-mcp-cli run-tool tool-set-enabled-state --input-file - <<'EOF'
{"param": "value"}
EOF

Troubleshooting

If unity-mcp-cli is not found, either install it globally (npm install -g unity-mcp-cli) or use npx unity-mcp-cli instead. Read the /unity-initial-setup skill for detailed installation instructions.

Input

Name	Type	Required	Description
tools	string	Yes	Array of tools with their desired enabled state. RQL: [ToolToggleInput]
includeLogs	boolean	No	Include operation logs in the result. Default: false

Input JSON Schema

{
  "type": "object",
  "properties": {
    "tools": {
      "type": "string"
    },
    "includeLogs": {
      "type": "boolean"
    }
  },
  "required": [
    "tools"
  ]
}

Output

This tool does not return structured output.