How do I use Agent Orchestrator MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Agent Orchestrator MCP Server create a research agent for competitor analysis" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Agent Orchestrator MCP Server

By MEOK AI Labs — Sovereign AI tools for everyone.

Multi-agent task management system for AI applications. Create agents with roles and capabilities, delegate tasks with trust-based routing, coordinate file access, run focused sprints, and monitor performance through a unified dashboard.

MCPize MIT License MEOK AI Labs

Tools

Tool	Description
`create_agent`	Create a new agent with name, role, and capabilities
`list_agents`	List all registered agents with trust levels and status
`delegate_task`	Delegate a task to an agent or auto-route to best match
`complete_task`	Mark a task as completed or failed
`acquire_files`	Acquire file locks for coordinated multi-agent work
`release_files`	Release file locks held by an agent
`start_sprint`	Start a focused sprint with goals and a time limit
`complete_sprint`	Complete a sprint and record achieved goals
`get_dashboard`	Get the full orchestration dashboard
`get_task_queue`	Get the task queue filtered by status

Quick Start

pip install mcp
git clone https://github.com/CSOAI-ORG/agent-orchestrator-mcp.git
cd agent-orchestrator-mcp
python server.py

Claude Desktop Config

{
  "mcpServers": {
    "agent-orchestrator": {
      "command": "python",
      "args": ["server.py"],
      "cwd": "/path/to/agent-orchestrator-mcp"
    }
  }
}

Pricing

Plan	Price	Requests
Free	$0/mo	100 calls/day, 10 agents max
Pro	$9/mo	Unlimited agents + webhook notifications
Enterprise	Contact us	Custom + LLM-powered routing