🔌

hidai25/eval-view

Name: hidai25/eval-view
Author: hidai25

Apache-2.0API key required

](https://glama.ai/mcp/servers/hidai25/eval-view) 🐍 🏠 🍎 🪟 🐧 - Regression testing framework for AI agents. Save golden baselines, detect behavioral drift, and block regressions in CI. Works with L

PythonAI & LLMs

Install

npx -y evalview

Required environment variables

OPENAI_API_KEYSet in your MCP config

ANTHROPIC_API_KEYSet in your MCP config

claude_desktop_config.json

{
  "mcpServers": {
    "hidai25-eval-view": {
      "command": "npx",
      "args": [
        "-y",
        "evalview"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>"
      }
    }
  }
}

Add this to your Claude Desktop config file. Find it at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS.

More Python MCP servers

🔌

microsoft/markitdown

🎖️ 🐍 🏠 - MCP tool access to MarkItDown -- a library that converts many file formats (local or remote) to Markdown for LLM consumption.

🔌

netdata/netdata#Netdata

🎖️ 🏠 ☁️ 📟 🍎 🪟 🐧 - Discovery, exploration, reporting and root cause analysis using all observability data, including metrics, logs, systems, containers, processes, and network connections

🔌

upstash/context7

📇 ☁️ - Up-to-date code documentation for LLMs and AI code editors.

🔌

mindsdb/mindsdb

Connect and unify data across various platforms and databases with .

CLAUDE.md rules for Python

🐍Python FastAPI Expert 🎸Django Web Framework 📋Mindx CLAUDE.md

Browse all CLAUDE.md rules →