AI Workbench MCP

Overview

AI Workbench MCP is a Model Context Protocol server built for Goose, designed to manage acceptance evidence, validation gates, and analytics within your development workflow. Any MCP-compatible AI assistant can call its tools directly, letting the model decide when to use them during conversations or agent runs.

The server runs locally on your machine via the Python package ai-workbench-mcp, installed through uvx. It communicates over stdio with no authentication required, making it ready to use immediately. The latest release is v0.6.0a0 under the Apache-2.0 license, with source code available at hrishikesh-thakre/ai-workbench-mcp on GitHub.

AI Workbench MCP is categorized under AI & Agents and integrates with all MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this server, claim your listing to verify ownership, earn the Verified badge, and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "ai_workbench_mcp": {
      "command": "uvx",
      "args": [
        "ai-workbench-mcp"
      ]
    }
  }
}