# Evalview MCP (MCP server)

> Evalview MCP is an MCP server that adds cloud and DevOps tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Regression testing for AI agents. Golden baselines, CI/CD, LangGraph, CrewAI, OpenAI, Claude. It has 137 GitHub stars, is released under the Apache-2.0 license and runs locally with uvx evalview.

Snapshot testing for AI agents. Record what your agent does today. Get told when it silently changes. Your agent returns 200 and looks fine. But a model update, a provider change, or a one-line prompt edit just made it skip a clarification, call the wrong tool, or quietly drop output quality. Your tests still pass. Your users notice before you do.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/hidai25/eval-view |
| GitHub stars | 137 |
| License | Apache-2.0 |
| Language | Python |
| Transport | stdio |
| Packages | pypi: evalview |
| Remote URL | none |
| Needs API key | no |
| Official | no |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code |
| Category | Cloud & DevOps |
| Latest release | v0.8.1 (Jul 26, 2026) |
| Last commit | Sep 5, 2026 |
| MCP registry name | io.github.hidai25/evalview-mcp |

## Install

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "evalview-mcp": {
      "command": "uvx",
      "args": [
        "evalview"
      ],
      "env": {
        "OPENAI_API_KEY": "your-value"
      }
    }
  }
}
```

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --env OPENAI_API_KEY=your-value --transport stdio evalview-mcp -- uvx evalview
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "evalview-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "evalview"
      ],
      "env": {
        "OPENAI_API_KEY": "your-value"
      }
    }
  }
}
```

Project file; use ~/.cursor/mcp.json to enable it in every project.

### VS Code (.vscode/mcp.json)

```json
{
  "inputs": [
    {
      "type": "promptString",
      "id": "openai_api_key",
      "description": "OPENAI_API_KEY",
      "password": true
    }
  ],
  "servers": {
    "evalview-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "evalview"
      ],
      "env": {
        "OPENAI_API_KEY": "${input:openai_api_key}"
      }
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Environment variables

- `OPENAI_API_KEY` (secret): OpenAI API key for LLM-as-judge output quality scoring. Optional — deterministic tool/sequence evaluation works without it.

## Similar MCP servers

- [Worldmonitor](https://appsgit.com/mcp-servers/worldmonitor): Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface. (87,920 stars, AGPL-3.0)
- [Netdata](https://appsgit.com/mcp-servers/netdata): Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection. (80,817 stars, GPL-3.0, needs API key)
- [openstatus](https://appsgit.com/mcp-servers/openstatus): Manage monitors, status pages, incidents and maintenances in your openstatus workspace. (9,171 stars, AGPL-3.0, official)
- [MCP Server Cloudflare](https://appsgit.com/mcp-servers/mcp-server-cloudflare): Model Context Protocol (MCP) is a new, standardized protocol for managing context between large language models (LLMs) and external systems. (4,360 stars, Apache-2.0, official, needs API key)
- [Dagu](https://appsgit.com/mcp-servers/dagu): Self-hostable workflow orchestrator for teams whose main work isn't orchestration. (4,289 stars, GPL-3.0)
- [Azure MCP Server](https://appsgit.com/mcp-servers/azure-mcp-server): All Azure MCP tools to create a seamless connection between AI agents and Azure services. (3,738 stars, MIT, official)

---

Canonical page: https://appsgit.com/mcp-servers/evalview-mcp
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed nightly.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.