ConvergeQA Reviews (Critique & Iterate)

Overview

ConvergeQA Reviews (Critique & Iterate) is an MCP server that enables multi-model critique and iteration of documents with public verification receipts. Any MCP-compatible AI assistant can invoke its tools to perform document reviews, with the model deciding when and how to apply them during conversation or agent runs.

The server runs locally via the convergeqa-mcp package installed with uvx. It requires an API key for authentication and communicates over stdio on your machine. The current release is v0.2.0, published under the MIT license with source code available at convergeqa/convergeqa-mcp on GitHub.

Listed under AI & Agents, ConvergeQA Reviews (Critique & Iterate) works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others throughout the ecosystem. If you maintain this server for convergeqa, claim your listing to earn a Verified badge and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "convergeqa_reviews_critique_iterate": {
      "command": "uvx",
      "args": [
        "convergeqa-mcp"
      ]
    }
  }
}