AI Workbench MCP

About AI Workbench MCP

Use AI Workbench MCP with your agent

claude mcp add ai-workbench-mcp -- uvx ai-workbench-mcp

{
  "mcpServers": {
    "ai-workbench-mcp": {
      "command": "uvx",
      "args": [
        "ai-workbench-mcp"
      ]
    }
  }
}

Frequently asked questions

What is AI Workbench MCP?

AI Workbench MCP is an MCP (Model Context Protocol) server by hrishikesh-thakre in the Research & Data category. Goose-first MCP server for Workbench-owned acceptance evidence, validation gates, and analytics.

How do I connect AI Workbench MCP to Claude, Cursor, or another MCP client?

Install AI Workbench MCP from its pypi package (ai-workbench-mcp) and register it under "mcpServers" in your client's MCP configuration — for example claude_desktop_config.json or Cursor's mcp.json — then restart the client.

Is AI Workbench MCP open source?

Yes — the source code is public at github.com/hrishikesh-thakre/ai-workbench-mcp.

Can AI agents pay to use AI Workbench MCP?

Not yet through Loomal — AI Workbench MCP is listed as a free directory entry. If its maintainer verifies ownership, they can set per-call USDC pricing that agents pay over x402, with settlement on Base.