Evalview Mcp

Overview

Evalview Mcp is a regression testing server for AI agents that establishes golden baselines and integrates with CI/CD pipelines. It supports LangGraph, CrewAI, OpenAI, and Claude workflows, letting any MCP-compatible AI assistant call its tools directly to evaluate agent performance and behavior.

The server runs locally via uvx evalview, speaking MCP over stdio on your machine. It requires an API key for authentication. Version v0.6.0 is available now under the Apache-2.0 license, with full source code at hidai25/eval-view on GitHub where the project has gathered 132 stars.

Evalview Mcp appears in the AI & Agents category on mcp.site and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others. If you maintain this server for hidai25, claim this listing to verify ownership and keep it up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "evalview_mcp": {
      "command": "uvx",
      "args": [
        "evalview"
      ]
    }
  }
}