Hive Coordinator
mcp_m7_hive_coordinatorOrchestrate multiagent collaboration for complex tasks by forming expert teams, decomposing work, and validating results.
Instructions
Orchestrate multiagent collaboration for complex tasks using M7 Hive system.
v3.8.0 Features:
DYNAMIC MODE (default): AI creates optimal expert team for each task
PLANNED MODE (new): CNP auction-based coordination with task decomposition
MODEL SELECTION: Best model chosen per agent based on LiveBench benchmarks
SELF-LEARNING: System improves over time based on results
GATEKEEPERS: Style, Architecture, Security validation
Use mode="dynamic" for quick expert analysis (default). Use mode="planned" for complex tasks requiring decomposition and validation. Use mode="fixed" for legacy behavior with predefined agents.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"task": "<task>"
},
"name": "mcp_m7_hive_coordinator"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Execution mode: "dynamic" (AI team, default), "planned" (CNP auction-based, v3.8.0+), or "fixed" (legacy) | dynamic |
| task | Yes | Task description for multiagent analysis | |
| agents | No | Which agents to involve (only used in "fixed" mode, auto-selected if not specified) | |
| priority | No | Optimization priority | quality |
| max_rounds | No | Maximum debate rounds before fallback | |
| debate_mode | No | Enable agent debates for consensus | |
| plannerOptions | No | Options for planned mode (v3.8.0+) |