Verlon AI MCP

Overview

Verlon AI MCP is a Model Context Protocol (MCP) server: Inspect and manage Verlon AI gates, logs, recommendations, and experiments from any MCP client. In practice that means any MCP-compatible AI assistant can call Verlon AI MCP's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the npm package @verlon-ai/mcp speaks MCP over stdio on your machine. Configuration happens through environment variables — you'll need VERLON_API_KEY. The current release is v0.4.0, published under the MIT license, with source at verlon-ai/mcp on GitHub.

Verlon AI MCP is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Verlon AI MCP for verlon.ai, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "verlon_ai_mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@verlon-ai/mcp"
      ],
      "env": {
        "VERLON_API_KEY": "<verlon-api-key>"
      }
    }
  }
}

Requires VERLON_API_KEY