Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@coreason_multi_agent_debate debate the ethical implications of autonomous vehicles"
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.
Dynamic multi agent debate MCP server
Python 3.14+
uv
Clone the repository:
git clone https://github.com/CoReason-AI/coreason_multi_agent_debate.git
cd coreason_multi_agent_debateInstall dependencies:
uv sync --all-extras --devRun the linter:
uv run pre-commit run --all-filesRun the tests:
uv run pytestStructured multi‑persona debate tool.
Call sequence (typical):
Each persona registers once with action:"register".
Personas alternate action:"argue" (fresh point) or "rebut" (counter a targetAgentId).
A special persona (or either side) issues action:"judge" with a verdict text (first line should be "pro", "con", or "inconclusive").
Set needsMoreRounds:false only when the debate is finished and a verdict stands.
Parameters:
agentId (string) : "pro", "con", "judge", or any custom ID
round (int ≥1) : Debate round number
action (string) : "register" | "argue" | "rebut" | "judge"
content (string, optional) : Argument text or verdict
targetAgentId (string opt.) : Agent being rebutted (only for action:"rebut")
needsMoreRounds (boolean) : True if additional debate rounds desired
| Name | Required | Description | Default |
|---|---|---|---|
| round | Yes | ||
| action | Yes | ||
| agentId | Yes | ||
| content | No | ||
| targetAgentId | No | ||
| needsMoreRounds | Yes |
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.7multiagentdebateScored across 1 tool
Only one tool exists, so there is no possibility of confusion between tools. The tool's purpose is clearly defined.
The single tool name 'multiagentdebate' is descriptive and uses consistent camelCase. There are no naming conflicts to evaluate.
With just one tool, the server is minimal. While the tool is comprehensive for debates, a single tool feels slightly thin for typical MCP servers, but it is borderline acceptable for a niche function.
The tool covers the full debate lifecycle: registration, argument, rebuttal, and judging. All necessary actions are included, with no obvious gaps for the intended domain.
MCP server for building and testing AI agents with multi-model experimentation and insights.
AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.
NeuralBrain MCP Server - RAG, Vector Memory, LLM Routing, Agent Identity, x402 Payments
LLM Orchestration Agent (Mcp)