Skills Plugins MCP Prompt Model 导航 博客 资讯 我的中心
AI Agents #TypeScript#混合部署#MIT

iris-eval/mcp-server

MCP-native agent evaluation and observability server. Log traces, evaluate output quality with 12 built-in rules (PII detection, prompt injection, cost thresholds), and track agent costs. Real-time dashboard, OTel-compatible spans. Self-hosted, MIT licensed.

AI Agents npm 0 platforms 0 features

Install

npx -y @iris-eval/mcp-server

Paste the configuration above into your MCP client config (claude_desktop_config.json for Claude Desktop) and restart the client.

{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@iris-eval/mcp-server"
      ],
      "env": {
        "IRIS_PORT": "<IRIS_PORT>",
        "IRIS_API_KEY": "<IRIS_API_KEY>",
        "IRIS_DB_PATH": "<IRIS_DB_PATH>",
        "IRIS_DASHBOARD": "<IRIS_DASHBOARD>",
        "IRIS_LOG_LEVEL": "<IRIS_LOG_LEVEL>",
        "IRIS_TRANSPORT": "<IRIS_TRANSPORT>",
        "IRIS_ALLOWED_ORIGINS": "<IRIS_ALLOWED_ORIGINS>"
      }
    }
  }
}

Paste the configuration above into your MCP client config (claude_desktop_config.json for Claude Desktop) and restart the client.

Sources: public MCP Server directories. This is an independent third-party directory with no affiliation to or endorsement from the maintainers of the listed servers.

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。