This MCP server provides pipeline-driven task management for AI coding agents, enabling multi-agent collaboration and real-time task tracking through a kanban dashboard.
From the registry: Pipeline task management for AI agents - stages, dependencies, artifacts, claiming

Please install the `agent-tasks` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js >= 20.11** — Required runtime (https://nodejs.org/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["agent-tasks"]
- optional environment variables:
- `AGENT_TASKS_DB`: SQLite database path (example: `~/.agent-tasks/agent-tasks.db`)
- `AGENT_TASKS_PORT`: Dashboard HTTP/WebSocket port (example: `3422`)
- `AGENT_COMM_URL`: Agent-comm REST URL for bridge notifications (example: `http://localhost:3421`)
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AGENT_TASKS_DBrequiredSQLite database file path.AGENT_TASKS_PORTrequiredDashboard HTTP/WebSocket port.AGENT_COMM_URLrequiredAgent-comm REST URL for bridge notifications.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.