Skip to main content
Glama

Task Master

by eyaltoledano

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
XAI_API_KEYNoAPI key for xAI (for research or main model)
GOOGLE_API_KEYNoAPI key for Google Gemini models
OLLAMA_API_KEYNoAPI key for Ollama models
OPENAI_API_KEYNoAPI key for OpenAI models
MISTRAL_API_KEYNoAPI key for Mistral models
ANTHROPIC_API_KEYNoAPI key for Anthropic Claude models
OPENROUTER_API_KEYNoAPI key for OpenRouter (for research or main model)
PERPLEXITY_API_KEYNoAPI key for Perplexity (for research model)
AZURE_OPENAI_API_KEYNoAPI key for Azure OpenAI models

Schema

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Tools

Functions exposed to the LLM to take actions

NameDescription
initialize_project

Initializes a new Task Master project structure by calling the core initialization logic. Creates necessary folders and configuration files for Task Master in the current directory.

models

Get information about available AI models or set model configurations. Run without arguments to get the current model configuration and API key status for the selected model providers.

rules

Add or remove rule profiles from the project.

parse_prd

Parse a Product Requirements Document (PRD) text file to automatically generate initial tasks. Reinitializing the project is not necessary to run this tool. It is recommended to run parse-prd after initializing the project and creating/importing a prd.txt file in the project root's .taskmaster/docs directory.

analyze_project_complexity

Analyze task complexity and generate expansion recommendations.

expand_task

Expand a task into subtasks for detailed implementation

expand_all

Expand all pending tasks into subtasks based on complexity or defaults

get_tasks

Get all tasks from Task Master, optionally filtering by status and including subtasks.

get_task

Get detailed information about a specific task

next_task

Find the next task to work on based on dependencies and status

complexity_report

Display the complexity analysis report in a readable format

set_task_status

Set the status of one or more tasks or subtasks.

generate

Generates individual task files in tasks/ directory based on tasks.json

add_task

Add a new task using AI

add_subtask

Add a subtask to an existing task

update

Update multiple upcoming tasks (with ID >= 'from' ID) based on new context or changes provided in the prompt. Use 'update_task' instead for a single specific task or 'update_subtask' for subtasks.

update_task

Updates a single task by ID with new information or context provided in the prompt.

update_subtask

Appends timestamped information to a specific subtask without replacing existing content. If you just want to update the subtask status, use set_task_status instead.

remove_task

Remove a task or subtask permanently from the tasks list

remove_subtask

Remove a subtask from its parent task

clear_subtasks

Clear subtasks from specified tasks

move_task

Move a task or subtask to a new position

add_dependency

Add a dependency relationship between two tasks

remove_dependency

Remove a dependency from a task

validate_dependencies

Check tasks for dependency issues (like circular references or links to non-existent tasks) without making changes.

fix_dependencies

Fix invalid dependencies in tasks automatically

response-language

Get or set the response language for the project

list_tags

List all available tags with task counts and metadata

add_tag

Create a new tag for organizing tasks in different contexts

delete_tag

Delete an existing tag and all its tasks

use_tag

Switch to a different tag context for task operations

rename_tag

Rename an existing tag

copy_tag

Copy an existing tag to create a new tag with all tasks and metadata

research

Perform AI-powered research queries with project context

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/eyaltoledano/claude-task-master'

If you have feedback or need assistance with the MCP directory API, please join our Discord server