Task Manager
Task Manager MCP server that provides structured task management capabilities for AI agents working on complex multi-step problems, enabling them to register tasks with dependencies and parent-child relationships, assess task complexity to automatically break down work into subtasks with missing knowledge requirements, and track status transitions through not-started, in-progress, and complete states. Built by Maik Schreiber, the implementation enforces workflow constraints like requiring task assessment before execution, ensuring parent tasks are in progress before subtasks can start, and validating all dependencies are complete before task initiation. Designed for agents handling complex projects that need systematic decomposition, dependency management, and progress tracking across interconnected work items, making it valuable for software development workflows, research projects, and any scenario requiring structured task orchestration with automatic knowledge gap identification.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
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/blizzy78/mcp-task-manager
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Task Manager 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.