# Ai Consensus

> Ai Consensus is an open-source MCP server for ai models and llm tooling. Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Website:** https://ai-consensus.ai
- **Repository:** https://github.com/thestevenjohnstone/ai-consensus-connector
- **MCP Registry name:** io.github.TheStevenJohnstone/ai-consensus
- **Categories:** [AI models and LLM tooling](https://ai-powered.com/categories/ai-and-llm)
- **Listing updated:** 2026-11-13

## About

Standing review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.

## Install

### Claude Code (Terminal)

```sh
claude mcp add ai-consensus --env AI_CONSENSUS_API_KEY='<AI_CONSENSUS_API_KEY>' -- npx -y ai-consensus-connector
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "ai-consensus": {
      "command": "npx",
      "args": [
        "-y",
        "ai-consensus-connector"
      ],
      "env": {
        "AI_CONSENSUS_API_KEY": "<AI_CONSENSUS_API_KEY>"
      }
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "ai-consensus": {
      "command": "npx",
      "args": [
        "-y",
        "ai-consensus-connector"
      ],
      "env": {
        "AI_CONSENSUS_API_KEY": "<AI_CONSENSUS_API_KEY>"
      }
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "ai-consensus": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "ai-consensus-connector"
      ],
      "env": {
        "AI_CONSENSUS_API_KEY": "<AI_CONSENSUS_API_KEY>"
      }
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "ai-consensus": {
      "command": "npx",
      "args": [
        "-y",
        "ai-consensus-connector"
      ],
      "env": {
        "AI_CONSENSUS_API_KEY": "<AI_CONSENSUS_API_KEY>"
      }
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "ai-consensus": {
      "command": "npx",
      "args": [
        "-y",
        "ai-consensus-connector"
      ],
      "env": {
        "AI_CONSENSUS_API_KEY": "<AI_CONSENSUS_API_KEY>"
      }
    }
  }
}
```

## FAQ

### Is Ai Consensus free?

Yes. Ai Consensus is open source, so you can use and self-host it for free.

### How do I add Ai Consensus to Claude Code?

Run this command in your terminal: claude mcp add ai-consensus --env AI_CONSENSUS_API_KEY='<AI_CONSENSUS_API_KEY>' -- npx -y ai-consensus-connector

### What are the best alternatives to Ai Consensus?

The closest alternatives to Ai Consensus are Synero AI Council, Consult, Amicus and Parley.

## Where this comes from

- Description: from the official MCP Registry entry.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Synero AI Council](https://ai-powered.com/mcp/synero-ai-council): Synero AI Council is a freemium MCP server for ai models and llm tooling.
- [Consult](https://ai-powered.com/mcp/consult): Consult is an open-source MCP server for developer tools.
- [Amicus](https://ai-powered.com/mcp/amicus): Amicus is a free MCP server for ai models and llm tooling.
- [Parley](https://ai-powered.com/mcp/parley-4): Parley is an open-source MCP server for ai models and llm tooling.

---
Source: https://ai-powered.com/mcp/ai-consensus
