claude-task-master/apps/docs/getting-started/quick-start/configuration-quick.mdx

---
title: Configuration
sidebarTitle: "Configuration"

---

Before getting started with Task Master, you'll need to set up your API keys. There are a couple of ways to do this depending on whether you're using the CLI or working inside MCP. It's also a good time to start getting familiar with the other configuration options available — even if you don’t need to adjust them yet, knowing what’s possible will help down the line.

## API Key Setup

Task Master uses environment variables to securely store provider API keys and optional endpoint URLs.

### MCP Usage: mcp.json file

For MCP/Cursor usage: Configure keys in the env section of your .cursor/mcp.json file.

```java .env lines icon="java"
{
	"mcpServers": {
		"task-master-ai": {
			"command": "npx",
			"args": ["-y", "task-master-ai"],
			"env": {
				"ANTHROPIC_API_KEY": "ANTHROPIC_API_KEY_HERE",
				"PERPLEXITY_API_KEY": "PERPLEXITY_API_KEY_HERE",
				"OPENAI_API_KEY": "OPENAI_API_KEY_HERE",
				"GOOGLE_API_KEY": "GOOGLE_API_KEY_HERE",
				"XAI_API_KEY": "XAI_API_KEY_HERE",
				"OPENROUTER_API_KEY": "OPENROUTER_API_KEY_HERE",
				"MISTRAL_API_KEY": "MISTRAL_API_KEY_HERE",
				"AZURE_OPENAI_API_KEY": "AZURE_OPENAI_API_KEY_HERE",
				"OLLAMA_API_KEY": "OLLAMA_API_KEY_HERE",
				"GITHUB_API_KEY": "GITHUB_API_KEY_HERE",
				"GROK_CLI_API_KEY": "GROK_CLI_API_KEY_HERE"
			}
		}
	}
}
```

### CLI Usage: `.env` File

Create a `.env` file in your project root and include the keys for the providers you plan to use:



```java .env lines icon="java"
# Required API keys for providers configured in .taskmaster/config.json
ANTHROPIC_API_KEY=sk-ant-api03-your-key-here
PERPLEXITY_API_KEY=pplx-your-key-here
# OPENAI_API_KEY=sk-your-key-here
# GOOGLE_API_KEY=AIzaSy...
# AZURE_OPENAI_API_KEY=your-azure-openai-api-key-here
# etc.

# Optional Endpoint Overrides
# Use a specific provider's base URL, e.g., for an OpenAI-compatible API
# OPENAI_BASE_URL=https://api.third-party.com/v1
#
# Azure OpenAI Configuration
# AZURE_OPENAI_ENDPOINT=https://your-resource-name.openai.azure.com/ or https://your-endpoint-name.cognitiveservices.azure.com/openai/deployments
# OLLAMA_BASE_URL=http://custom-ollama-host:11434/api

# Google Vertex AI Configuration (Required if using 'vertex' provider)
# VERTEX_PROJECT_ID=your-gcp-project-id

# Grok CLI Configuration (Required if using 'grok-cli' provider)
# GROK_CLI_API_KEY=your-grok-api-key-here

# Codebase Analysis Feature Control
# TASKMASTER_ENABLE_CODEBASE_ANALYSIS=true  # Enable codebase analysis features (default: true)
```

## Grok Provider Setup

Task Master now supports Grok models from xAI with full codebase context awareness. This is especially useful for AI operations that benefit from understanding your entire project structure.

### Getting Started with Grok

1. **Get your Grok API key** from [console.x.ai](https://console.x.ai)
2. **Set the environment variable**:
   ```bash
   export GROK_CLI_API_KEY="your-api-key-here"
   ```
3. **Configure Task Master to use Grok**:
   ```bash
   task-master models --set-main grok-beta
   # or
   task-master models --set-research grok-beta
   # or  
   task-master models --set-fallback grok-beta
   ```

### Key Features

- **Full codebase context**: Grok models can analyze your entire project when generating tasks or parsing PRDs
- **xAI model access**: Support for latest Grok models (grok-2, grok-3, grok-4, etc.)
- **Code-aware task generation**: Create more accurate and contextual tasks based on your actual codebase
- **Intelligent PRD parsing**: Parse requirements with understanding of your existing code structure

### Available Models

- `grok-beta` - Latest Grok model with codebase context
- `grok-vision-beta` - Grok with vision capabilities and codebase context

<Note>
The Grok CLI provider integrates with xAI's Grok models via [grok-cli](https://github.com/superagent-ai/grok-cli) by Superagent AI and can also use the local Grok CLI configuration file (`~/.grok/user-settings.json`) if available.
</Note>

## What Else Can Be Configured?

The main configuration file (`.taskmaster/config.json`) allows you to control nearly every aspect of Task Master’s behavior. Here’s a high-level look at what you can customize:

<Tip>
You don’t need to configure everything up front. Most settings can be left as defaults or updated later as your workflow evolves.
</Tip>

<Accordion title="View Configuration Options">

### Models and Providers
- Role-based model setup: `main`, `research`, `fallback`
- Provider selection (Anthropic, OpenAI, Perplexity, etc.)
- Model IDs per role
- Temperature, max tokens, and other generation settings
- Custom base URLs for OpenAI-compatible APIs

### Global Settings
- `logLevel`: Logging verbosity
- `debug`: Enable/disable debug mode
- `projectName`: Optional name for your project
- `defaultTag`: Default tag for task grouping
- `defaultSubtasks`: Number of subtasks to auto-generate
- `defaultPriority`: Priority level for new tasks

### Codebase Analysis Control
- `TASKMASTER_ENABLE_CODEBASE_ANALYSIS`: Control whether codebase analysis features are enabled
  - Can be set via environment variables, MCP configuration, or project config files
  - Priority order: `.env` > MCP session env > `.taskmaster/config.json`
  - Default: `true`
  - When enabled, allows providers like Claude Code and Gemini CLI to analyze your project structure for more contextual task generation

### API Endpoint Overrides
- `ollamaBaseURL`: Custom Ollama server URL
- `azureBaseURL`: Global Azure endpoint
- `vertexProjectId`: Google Vertex AI project ID
- `vertexLocation`: Region for Vertex AI models

### Tag and Git Integration
- Default tag context per project
- Support for task isolation by tag
- Manual tag creation from Git branches

### State Management
- Active tag tracking
- Migration state
- Last tag switch timestamp

</Accordion>

<Note>
For advanced configuration options and detailed customization, see our [Advanced Configuration Guide](/docs/best-practices/configuration-advanced) page.
</Note>