Configure Claude Task Master AI for VS Code MCP integration

- Updated .cursor/mcp.json to use local Nix-built Task Master binary
- Configured Task Master to use local Ollama models via OpenAI-compatible API
- Set up three models: qwen3:4b (main), deepseek-r1:1.5b (research), gemma3:4b-it-qat (fallback)
- Created comprehensive integration status documentation
- Task Master successfully running as MCP server with 23+ available tools
- Ready for VS Code/Cursor AI chat integration

.taskmaster/config.json

@@ -0,0 +1,37 @@
+{
+  "models": {
+    "main": {
+      "provider": "openai",
+      "modelId": "qwen3:4b",
+      "maxTokens": 4096,
+      "temperature": 0.2,
+      "baseURL": "http://grey-area:11434/v1"
+    },
+    "research": {
+      "provider": "openai",
+      "modelId": "deepseek-r1:1.5b",
+      "maxTokens": 4096,
+      "temperature": 0.1,
+      "baseURL": "http://grey-area:11434/v1"
+    },
+    "fallback": {
+      "provider": "openai",
+      "modelId": "gemma3:4b-it-qat",
+      "maxTokens": 4096,
+      "temperature": 0.3,
+      "baseURL": "http://grey-area:11434/v1"
+    }
+  },
+  "global": {
+    "logLevel": "info",
+    "debug": false,
+    "defaultSubtasks": 5,
+    "defaultPriority": "medium",
+    "projectName": "Home Lab Infrastructure",
+    "ollamaBaseURL": "http://grey-area:11434/v1",
+    "bedrockBaseURL": "https://bedrock.us-east-1.amazonaws.com",
+    "vertexProjectId": "your-gcp-project-id",
+    "vertexLocation": "us-central1",
+    "userId": "1234567890"
+  }
+}