This is a planning agent that estimates sprints, breaks down tasks, and flags risks while learning your team's velocity over time. The source repository shows it's actually part of ISG Agent 1, a governance-focused autonomous agent platform with constitution enforcement, adversarial self-testing, and cryptographic audit trails. The MCP server likely exposes planning capabilities from that larger system. You'd reach for this when you want AI-assisted sprint planning that adapts to your delivery patterns, though the documentation doesn't detail which specific planning operations are available through the MCP interface versus the full platform. The underlying system runs on Python 3.11+ with FastAPI and includes sandboxed skill execution.
claude mcp add --transport stdio io.github.dingdawg-dingdawg-planning-agent -- npx -y dingdawg-planning-agent