Task Master
This MCP server provides AI-driven task management capabilities for development workflows, built using Node.js with FastMCP and integrating multiple AI providers including Anthropic, OpenAI, Perplexity, and Google. It offers comprehensive project management tools including PRD parsing to generate initial tasks, task CRUD operations with dependency management, AI-powered task expansion into subtasks, complexity analysis, and tagged task contexts for organizing work across different project phases. The implementation uses a modular architecture with direct function wrappers, session-based environment variable handling, and context management for efficient AI operations, plus includes both CLI and MCP interfaces for flexible integration into development environments where teams need structured, AI-assisted project planning and task breakdown.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/eyaltoledano/claude-task-master
- Author type
- human
- Updated
- 2026-05-27
Use via MCP
Resolve Task Master from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.