# Multi Agent Debate Mcp

> Model Context Protocol Server agent debates

- **Type:** MCP server
- **Install:** `agentstack add mcp-albinjal-multi-agent-debate-mcp`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [albinjal](https://agentstack.voostack.com/s/albinjal)
- **Installs:** 0
- **Category:** [Integrations](https://agentstack.voostack.com/c/integrations)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [albinjal](https://github.com/albinjal)
- **Source:** https://github.com/albinjal/multi-agent-debate-mcp
- **Website:** https://www.npmjs.com/package/multi-agent-debate-mcp

## Install

```sh
agentstack add mcp-albinjal-multi-agent-debate-mcp
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Multi-Agent Debate MCP Server

An MCP server implementation that enables structured multi-agent debates between different personas. This server allows multiple AI agents to engage in formal debates with arguments, rebuttals, and judgments across multiple rounds.

## Features

- Register multiple agents with different personas (e.g., "pro", "con", "judge")
- Structured debate flow with organized rounds
- Colorized console output with beautiful terminal display
- Flexible agent IDs beyond just "pro" and "con"
- Automatic verdict tracking with rationale
- Round-based system with configurable progression

## Tools

### multiagentdebate

Facilitates structured multi-agent debates with arguments, rebuttals, and judgments.

**Inputs:**
- `agentId` (string): Unique identifier for the agent (e.g., "pro", "con", "judge")
- `round` (integer): Current debate round number (≥1)
- `action` (string): One of "register", "argue", "rebut", "judge"
- `content` (string, optional): The argument text or verdict content
- `targetAgentId` (string, optional): For rebuttals, specify which agent is being countered
- `needsMoreRounds` (boolean): Whether additional debate rounds are needed

## Usage

The Multi-Agent Debate tool is designed for:
- Structured debates between multiple AI personas
- Formal argumentation with rebuttals and counterpoints
- Multi-round discussions with judgment phases
- Complex decision-making processes requiring multiple perspectives
- Educational debate simulations
- Collaborative problem-solving through adversarial discussion

## Configuration

#### npx

```json
{
  "mcpServers": {
    "multi-agent-debate": {
      "command": "npx",
      "args": [
        "-y",
        "multi-agent-debate-mcp"
      ]
    }
  }
}
```

#### Docker

```json
{
  "mcpServers": {
    "multi-agent-debate": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/albinjal/multi-agent-debate-mcp:latest"
      ]
    }
  }
}
```

## Demo

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [albinjal](https://github.com/albinjal)
- **Source:** [albinjal/multi-agent-debate-mcp](https://github.com/albinjal/multi-agent-debate-mcp)
- **License:** MIT
- **Homepage:** https://www.npmjs.com/package/multi-agent-debate-mcp

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-albinjal-multi-agent-debate-mcp
- Seller: https://agentstack.voostack.com/s/albinjal
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.